Rico Sennrich


2024

pdf
Linear-time Minimum Bayes Risk Decoding with Reference Aggregation
Jannis Vamvas | Rico Sennrich
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Minimum Bayes Risk (MBR) decoding is a text generation technique that has been shown to improve the quality of machine translations, but is expensive, even if a sampling-based approximation is used. Besides requiring a large number of sampled sequences, it requires the pairwise calculation of a utility metric, which has quadratic complexity. In this paper, we propose to approximate pairwise metric scores with scores calculated against aggregated reference representations. This changes the complexity of utility estimation from O(n2) to O(n), while empirically preserving most of the quality gains of MBR decoding. We release our source code.

pdf
Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
Rico Sennrich | Jannis Vamvas | Alireza Mohammadshahi
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)

Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding objective, without either requiring retraining or external models. In source-contrastive decoding, we search for a translation that is probable given the correct input, but improbable given a random input segment. In language-contrastive decoding, we search for a translation that is probable, but improbable given the wrong language indicator token. Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations, reducing the number of translations with segment-level chrF2 below 10 by 67-83% on average across 57 tested translation directions. In a proof of concept on out-of-English translation, we also show that we can suppress off-target translations with large language models. We release code upon acceptance.

pdf
SignCLIP: Connecting Text and Sign Language by Contrastive Learning
Zifan Jiang | Gerard Sant | Amit Moryossef | Mathias Müller | Rico Sennrich | Sarah Ebling
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

We present SignCLIP, which re-purposes CLIP (Contrastive Language-Image Pretraining) to project spoken language text and sign language videos, two classes of natural languages of distinct modalities, into the same space. SignCLIP is an efficient method of learning useful visual representations for sign language processing from large-scale, multilingual video-text pairs, without directly optimizing for a specific task or sign language which is often of limited size.We pretrain SignCLIP on Spreadthesign, a prominent sign language dictionary consisting of ~500 thousand video clips in up to 44 sign languages, and evaluate it with various downstream datasets. SignCLIP discerns in-domain signing with notable text-to-video/video-to-text retrieval accuracy. It also performs competitively for out-of-domain downstream tasks such as isolated sign language recognition upon essential few-shot prompting or fine-tuning.We analyze the latent space formed by the spoken language text and sign language poses, which provides additional linguistic insights. Our code and models are openly available.

pdf
Evaluating Automatic Metrics with Incremental Machine Translation Systems
Guojun Wu | Shay B Cohen | Rico Sennrich
Findings of the Association for Computational Linguistics: EMNLP 2024

We introduce a dataset comprising commercial machine translations, gathered weekly over six years across 12 translation directions. Since human A/B testing is commonly used, we assume commercial systems improve over time, which enables us to evaluate machine translation (MT) metrics based on their preference for more recent translations. Our study not only confirms several prior findings, such as the advantage of neural metrics over non-neural ones, but also explores the debated issue of how MT quality affects metric reliability—an investigation that smaller datasets in previous research could not sufficiently explore. Overall, our research demonstrates the dataset’s value as a testbed for metric evaluation. We release our code.

pdf
Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?
Tannon Kew | Florian Schottmann | Rico Sennrich
Findings of the Association for Computational Linguistics: EMNLP 2024

The vast majority of today’s large language models (LLMs) are English-centric, having been pretrained predominantly on English text. Yet, in order to meet user expectations, models need to be able to respond appropriately in multiple languages once deployed in downstream applications. This requires strong cross-lingual transfer abilities.In this work, we investigate the minimal amount of multilinguality required during finetuning to elicit cross-lingual generalisation in English-centric LLMs. In experiments across four LLMs, we find that multilingual instruction tuning with as few as two to three languages is both necessary and sufficient to elicit effective cross-lingual generalisation, with the limiting factor being the degree to which a target language is seen during pretraining. Evaluations on five different tasks further reveal that multilingual instruction tuning is most beneficial for generative tasks that assume input/output language agreement, such as in chat settings, while being of less importance for highly structured classification-style tasks.

pdf
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
Marco Cognetta | Tatsuya Hiraoka | Rico Sennrich | Yuval Pinter | Naoaki Okazaki
Proceedings of the Fifth Workshop on Insights from Negative Results in NLP

We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a tokenization postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not been subjected to rigorous scientific scrutiny. While the removal of rare subwords is suggested as best practice in model implementations, both as a means to reduce model size and for improving model performance through robustness, our experiments indicate that, across a large space of hyperparameter settings, vocabulary trimming fails to consistently improve model performance, and is even prone to incurring heavy degradation.

pdf
Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models
Alireza Mohammadshahi | Jannis Vamvas | Rico Sennrich
Proceedings of the Fifth Workshop on Insights from Negative Results in NLP

Massively multilingual machine translation models allow for the translation of a large number of languages with a single model, but have limited performance on low- and very-low-resource translation directions. Pivoting via high-resource languages remains a strong strategy for low-resource directions, and in this paper we revisit ways of pivoting through multiple languages. Previous work has used a simple averaging of probability distributions from multiple paths, but we find that this performs worse than using a single pivot, and exacerbates the hallucination problem because the same hallucinations can be probable across different paths. We also propose MaxEns, a novel combination strategy that makes the output biased towards the most confident predictions, hypothesising that confident predictions are less prone to be hallucinations. We evaluate different strategies on the FLORES benchmark for 20 low-resource language directions, demonstrating that MaxEns improves translation quality for low-resource languages while reducing hallucination in translations, compared to both direct translation and an averaging approach. On average, multi-pivot strategies still lag behind using English as a single pivot language, raising the question of how to identify the best pivoting strategy for a given translation direction.

pdf
SwissSLi: The Multi-parallel Sign Language Corpus for Switzerland
Zifan Jiang | Anne Göhring | Amit Moryossef | Rico Sennrich | Sarah Ebling
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

In this work, we introduce SwissSLi, the first sign language corpus that contains parallel data of all three Swiss sign languages, namely Swiss German Sign Language (DSGS), French Sign Language of Switzerland (LSF-CH), and Italian Sign Language of Switzerland (LIS-CH). The data underlying this corpus originates from television programs in three spoken languages: German, French, and Italian. The programs have for the most part been translated into sign language by deaf translators, resulting in a unique, up to six-way multi-parallel dataset between spoken and sign languages. We describe and release the sign language videos and spoken language subtitles as well as the overall statistics and some derivatives of the raw material. These derived components include cropped videos, pose estimation, phrase/sign-segmented videos, and sentence-segmented subtitles, all of which facilitate downstream tasks such as sign language transcription (glossing) and machine translation. The corpus is publicly available on the SWISSUbase data platform for research purposes only under a CC BY-NC-SA 4.0 license.

pdf
Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect
Jannis Vamvas | Noëmi Aepli | Rico Sennrich
Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024)

Creating neural text encoders for written Swiss German is challenging due to a dearth of training data combined with dialectal variation. In this paper, we build on several existing multilingual encoders and adapt them to Swiss German using continued pre-training. Evaluation on three diverse downstream tasks shows that simply adding a Swiss German adapter to a modular encoder achieves 97.5% of fully monolithic adaptation performance. We further find that for the task of retrieving Swiss German sentences given Standard German queries, adapting a character-level model is more effective than the other adaptation strategies. We release our code and the models trained for our experiments.

2023

pdf
Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model
Chantal Amrhein | Florian Schottmann | Rico Sennrich | Samuel Läubli
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more gender-fair language by creating pseudo training data through linguistic rules. However, this approach is not practical for languages with more complex morphology than English. We hypothesise that creating training data in the reverse direction, i.e. starting from gender-fair text, is easier for morphologically complex languages and show that it matches the performance of state-of-the-art rewriting models for English. To eliminate the rule-based nature of data creation, we instead propose using machine translation models to create gender-biased text from real gender-fair text via round-trip translation. Our approach allows us to train a rewriting model for German without the need for elaborate handcrafted rules. The outputs of this model increased gender-fairness as shown in a human evaluation study.

pdf
What’s the Meaning of Superhuman Performance in Today’s NLU?
Simone Tedeschi | Johan Bos | Thierry Declerck | Jan Hajič | Daniel Hershcovich | Eduard Hovy | Alexander Koller | Simon Krek | Steven Schockaert | Rico Sennrich | Ekaterina Shutova | Roberto Navigli
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities in language understanding, reasoning, and reading comprehension. These PLMs have achieved impressive results on these benchmarks, even surpassing human performance in some cases. This has led to claims of superhuman capabilities and the provocative idea that certain tasks have been solved. In this position paper, we take a critical look at these claims and ask whether PLMs truly have superhuman abilities and what the current benchmarks are really evaluating. We show that these benchmarks have serious limitations affecting the comparison between humans and PLMs and provide recommendations for fairer and more transparent benchmarks.

pdf
NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages
Genta Indra Winata | Alham Fikri Aji | Samuel Cahyawijaya | Rahmad Mahendra | Fajri Koto | Ade Romadhony | Kemal Kurniawan | David Moeljadi | Radityo Eko Prasojo | Pascale Fung | Timothy Baldwin | Jey Han Lau | Rico Sennrich | Sebastian Ruder
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Natural language processing (NLP) has a significant impact on society via technologies such as machine translation and search engines. Despite its success, NLP technology is only widely available for high-resource languages such as English and Chinese, while it remains inaccessible to many languages due to the unavailability of data resources and benchmarks. In this work, we focus on developing resources for languages in Indonesia. Despite being the second most linguistically diverse country, most languages in Indonesia are categorized as endangered and some are even extinct. We develop the first-ever parallel resource for 10 low-resource languages in Indonesia. Our resource includes sentiment and machine translation datasets, and bilingual lexicons. We provide extensive analyses and describe challenges for creating such resources. We hope this work can spark NLP research on Indonesian and other underrepresented languages.

pdf
Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation
Biao Zhang | Barry Haddow | Rico Sennrich
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality. However, CTC demands an extra prediction layer over the vocabulary space, bringing in non-negligible model parameters and computational overheads, although this layer becomes useless at inference. In this paper, we re-examine the need for genuine vocabulary labels for CTC for regularization and explore strategies to reduce the CTC label space, targeting improved efficiency without quality degradation. We propose coarse labeling for CTC (CoLaCTC), which merges vocabulary labels via simple heuristic rules, such as using truncation, division or modulo (MOD) operations. Despite its simplicity, our experiments on 4 source and 8 target languages show that CoLaCTC with MOD particularly can compress the label space aggressively to 256 and even further, gaining training efficiency (1.18× ∼ 1.77× speedup depending on the original vocabulary size) yet still delivering comparable or better performance than the CTC baseline. We also show that CoLaCTC successfully generalizes to CTC regularization regardless of using transcript or translation for labeling.

pdf
Self-training Reduces Flicker in Retranslation-based Simultaneous Translation
Sukanta Sen | Rico Sennrich | Biao Zhang | Barry Haddow
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

In simultaneous translation, the retranslation approach has the advantage of requiring no modifications to the inference engine. However, in order to reduce the undesirable flicker in the output, previous work has resorted to increasing the latency through masking, and introducing specialised inference, thus losing the simplicity of the approach. In this work, we show that self-training improves the flicker-latency tradeoff, while maintaining similar translation quality to the original. Our analysis indicates that self-training reduces flicker by controlling monotonicity. Furthermore, self-training can be combined with biased beam search to further improve the flicker-latency tradeoff.

pdf
Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents
Jannis Vamvas | Rico Sennrich
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three unsupervised approaches that rely on a masked language model. To assess the approaches, we begin with basic English sentences and gradually move to more complex, cross-lingual document pairs. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels. However, all unsupervised approaches still leave a large margin of improvement.

pdf
Uncovering Hidden Consequences of Pre-training Objectives in Sequence-to-Sequence Models
Tannon Kew | Rico Sennrich
Findings of the Association for Computational Linguistics: ACL 2023

Some variants of self-supervised denoising objectives for pre-training encoder-decoder language models have been reported to have a negligible impact on downstream performance. Yet the design of these pre-training objectives leads to behavioural differences that can be uncovered with specific manipulations. We reproduce a recently proposed zero-shot control method and find that it is only successful on a subset of models. To understand what causes the difference in its effectiveness, we perform a set of controlled experiments, varying only the pre-training objective, and find unexpected interactions between the pre-training method and downstream controllability of models after fine-tuning. Our results show that different pre-training objectives have consequences that may not be visible in standard downstream evaluation, but which should be taken into account when developing models with controllability in mind.

pdf
SwissBERT: The Multilingual Language Model for Switzerland
Jannis Vamvas | Johannes Graën | Rico Sennrich
Proceedings of the 8th edition of the Swiss Text Analytics Conference

pdf
Trained MT Metrics Learn to Cope with Machine-translated References
Jannis Vamvas | Tobias Domhan | Sony Trenous | Rico Sennrich | Eva Hasler
Proceedings of the Eighth Conference on Machine Translation

Neural metrics trained on human evaluations of MT tend to correlate well with human judgments, but their behavior is not fully understood. In this paper, we perform a controlled experiment and compare a baseline metric that has not been trained on human evaluations (Prism) to a trained version of the same metric (Prism+FT). Surprisingly, we find that Prism+FT becomes more robust to machine-translated references, which are a notorious problem in MT evaluation. This suggests that the effects of metric training go beyond the intended effect of improving overall correlation with human judgments.

pdf
A Benchmark for Evaluating Machine Translation Metrics on Dialects without Standard Orthography
Noëmi Aepli | Chantal Amrhein | Florian Schottmann | Rico Sennrich
Proceedings of the Eighth Conference on Machine Translation

For sensible progress in natural language processing, it is important that we are aware of the limitations of the evaluation metrics we use. In this work, we evaluate how robust metrics are to non-standardized dialects, i.e. spelling differences in language varieties that do not have a standard orthography. To investigate this, we collect a dataset of human translations and human judgments for automatic machine translations from English to two Swiss German dialects. We further create a challenge set for dialect variation and benchmark existing metrics’ performances. Our results show that existing metrics cannot reliably evaluate Swiss German text generation outputs, especially on segment level. We propose initial design adaptations that increase robustness in the face of non-standardized dialects, although there remains much room for further improvement. The dataset, code, and models are available here: https://github.com/textshuttle/dialect_eval

2022

pdf
Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET
Chantal Amrhein | Rico Sennrich
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Neural metrics have achieved impressive correlation with human judgements in the evaluation of machine translation systems, but before we can safely optimise towards such metrics, we should be aware of (and ideally eliminate) biases toward bad translations that receive high scores. Our experiments show that sample-based Minimum Bayes Risk decoding can be used to explore and quantify such weaknesses. When applying this strategy to COMET for en-de and de-en, we find that COMET models are not sensitive enough to discrepancies in numbers and named entities. We further show that these biases are hard to fully remove by simply training on additional synthetic data and release our code and data for facilitating further experiments.

pdf
As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning
Jannis Vamvas | Rico Sennrich
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Omission and addition of content is a typical issue in neural machine translation. We propose a method for detecting such phenomena with off-the-shelf translation models. Using contrastive conditioning, we compare the likelihood of a full sequence under a translation model to the likelihood of its parts, given the corresponding source or target sequence. This allows to pinpoint superfluous words in the translation and untranslated words in the source even in the absence of a reference translation. The accuracy of our method is comparable to a supervised method that requires a custom quality estimation model.

pdf
Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level Noise
Noëmi Aepli | Rico Sennrich
Findings of the Association for Computational Linguistics: ACL 2022

Cross-lingual transfer between a high-resource language and its dialects or closely related language varieties should be facilitated by their similarity. However, current approaches that operate in the embedding space do not take surface similarity into account. This work presents a simple yet effective strategy to improve cross-lingual transfer between closely related varieties. We propose to augment the data of the high-resource source language with character-level noise to make the model more robust towards spelling variations. Our strategy shows consistent improvements over several languages and tasks: Zero-shot transfer of POS tagging and topic identification between language varieties from the Finnic, West and North Germanic, and Western Romance language branches. Our work provides evidence for the usefulness of simple surface-level noise in improving transfer between language varieties.

pdf
NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures
Jannis Vamvas | Rico Sennrich
Findings of the Association for Computational Linguistics: EMNLP 2022

Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation cross-likelihood, which has not been studied so far. We analyze these measures in the common framework of multilingual NMT, releasing the NMTScore library. Compared to baselines such as sentence embeddings, translation-based measures prove competitive in paraphrase identification and are more robust against adversarial or multilingual input, especially if proper normalization is applied. When used for reference-based evaluation of data-to-text generation in 2 tasks and 17 languages, translation-based measures show a relatively high correlation to human judgments.

pdf
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
Yuchen Jiang | Tianyu Liu | Shuming Ma | Dongdong Zhang | Jian Yang | Haoyang Huang | Rico Sennrich | Ryan Cotterell | Mrinmaya Sachan | Ming Zhou
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Standard automatic metrics, e.g. BLEU, are not reliable for document-level MT evaluation. They can neither distinguish document-level improvements in translation quality from sentence-level ones, nor identify the discourse phenomena that cause context-agnostic translations. This paper introduces a novel automatic metric BlonDe to widen the scope of automatic MT evaluation from sentence to document level. BlonDe takes discourse coherence into consideration by categorizing discourse-related spans and calculating the similarity-based F1 measure of categorized spans. We conduct extensive comparisons on a newly constructed dataset BWB. The experimental results show that BlonDe possesses better selectivity and interpretability at the document-level, and is more sensitive to document-level nuances. In a large-scale human study, BlonDe also achieves significantly higher Pearson’s r correlation with human judgments compared to previous metrics.

pdf bib
Distributionally Robust Recurrent Decoders with Random Network Distillation
Antonio Valerio Miceli Barone | Alexandra Birch | Rico Sennrich
Proceedings of the 7th Workshop on Representation Learning for NLP

Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when processing out-of-domain (OOD) text. This has been attributed to “shortcut learning””:" relying on weak correlations over arbitrary large contexts. We propose a method based on OOD detection with Random Network Distillation to allow an autoregressive language model to automatically disregard OOD context during inference, smoothly transitioning towards a less expressive but more robust model as the data becomes more OOD, while retaining its full context capability when operating in-distribution. We apply our method to a GRU architecture, demonstrating improvements on multiple language modeling (LM) datasets.

2021

pdf
Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation
Mathias Müller | Rico Sennrich
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search – the de facto standard inference algorithm in NMT – and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead. In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.

pdf
Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation
Elena Voita | Rico Sennrich | Ivan Titov
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

In Neural Machine Translation (and, more generally, conditional language modeling), the generation of a target token is influenced by two types of context: the source and the prefix of the target sequence. While many attempts to understand the internal workings of NMT models have been made, none of them explicitly evaluates relative source and target contributions to a generation decision. We argue that this relative contribution can be evaluated by adopting a variant of Layerwise Relevance Propagation (LRP). Its underlying ‘conservation principle’ makes relevance propagation unique: differently from other methods, it evaluates not an abstract quantity reflecting token importance, but the proportion of each token’s influence. We extend LRP to the Transformer and conduct an analysis of NMT models which explicitly evaluates the source and target relative contributions to the generation process. We analyze changes in these contributions when conditioning on different types of prefixes, when varying the training objective or the amount of training data, and during the training process. We find that models trained with more data tend to rely on source information more and to have more sharp token contributions; the training process is non-monotonic with several stages of different nature.

pdf
Beyond Sentence-Level End-to-End Speech Translation: Context Helps
Biao Zhang | Ivan Titov | Barry Haddow | Rico Sennrich
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive experiments using a simple concatenation-based context-aware ST model, paired with adaptive feature selection on speech encodings for computational efficiency. We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. Our results on the MuST-C benchmark with Transformer demonstrate the effectiveness of context to E2E ST. Compared to sentence-level ST, context-aware ST obtains better translation quality (+0.18-2.61 BLEU), improves pronoun and homophone translation, shows better robustness to (artificial) audio segmentation errors, and reduces latency and flicker to deliver higher quality for simultaneous translation.

pdf
On the Limits of Minimal Pairs in Contrastive Evaluation
Jannis Vamvas | Rico Sennrich
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Minimal sentence pairs are frequently used to analyze the behavior of language models. It is often assumed that model behavior on contrastive pairs is predictive of model behavior at large. We argue that two conditions are necessary for this assumption to hold: First, a tested hypothesis should be well-motivated, since experiments show that contrastive evaluation can lead to false positives. Secondly, test data should be chosen such as to minimize distributional discrepancy between evaluation time and deployment time. For a good approximation of deployment-time decoding, we recommend that minimal pairs are created based on machine-generated text, as opposed to human-written references. We present a contrastive evaluation suite for English–German MT that implements this recommendation.

pdf
ELITR Multilingual Live Subtitling: Demo and Strategy
Ondřej Bojar | Dominik Macháček | Sangeet Sagar | Otakar Smrž | Jonáš Kratochvíl | Peter Polák | Ebrahim Ansari | Mohammad Mahmoudi | Rishu Kumar | Dario Franceschini | Chiara Canton | Ivan Simonini | Thai-Son Nguyen | Felix Schneider | Sebastian Stüker | Alex Waibel | Barry Haddow | Rico Sennrich | Philip Williams
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

This paper presents an automatic speech translation system aimed at live subtitling of conference presentations. We describe the overall architecture and key processing components. More importantly, we explain our strategy for building a complex system for end-users from numerous individual components, each of which has been tested only in laboratory conditions. The system is a working prototype that is routinely tested in recognizing English, Czech, and German speech and presenting it translated simultaneously into 42 target languages.

pdf
Sparse Attention with Linear Units
Biao Zhang | Ivan Titov | Rico Sennrich
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than previously proposed sparse attention mechanisms. We apply ReLA to the Transformer and conduct experiments on five machine translation tasks. ReLA achieves translation performance comparable to several strong baselines, with training and decoding speed similar to that of the vanilla attention. Our analysis shows that ReLA delivers high sparsity rate and head diversity, and the induced cross attention achieves better accuracy with respect to source-target word alignment than recent sparsified softmax-based models. Intriguingly, ReLA heads also learn to attend to nothing (i.e. ‘switch off’) for some queries, which is not possible with sparsified softmax alternatives.

pdf
Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT
Elena Voita | Rico Sennrich | Ivan Titov
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite neural machine translation being de-facto standard, it is still not clear how NMT models acquire different competences over the course of training, and how this mirrors the different models in traditional SMT. In this work, we look at the competences related to three core SMT components and find that during training, NMT first focuses on learning target-side language modeling, then improves translation quality approaching word-by-word translation, and finally learns more complicated reordering patterns. We show that this behavior holds for several models and language pairs. Additionally, we explain how such an understanding of the training process can be useful in practice and, as an example, show how it can be used to improve vanilla non-autoregressive neural machine translation by guiding teacher model selection.

pdf
Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution
Denis Emelin | Rico Sennrich
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Winograd schemas are a well-established tool for evaluating coreference resolution (CoR) and commonsense reasoning (CSR) capabilities of computational models. So far, schemas remained largely confined to English, limiting their utility in multilingual settings. This work presents Wino-X, a parallel dataset of German, French, and Russian schemas, aligned with their English counterparts. We use this resource to investigate whether neural machine translation (NMT) models can perform CoR that requires commonsense knowledge and whether multilingual language models (MLLMs) are capable of CSR across multiple languages. Our findings show Wino-X to be exceptionally challenging for NMT systems that are prone to undesirable biases and unable to detect disambiguating information. We quantify biases using established statistical methods and define ways to address both of these issues. We furthermore present evidence of active cross-lingual knowledge transfer in MLLMs, whereby fine-tuning models on English schemas yields CSR improvements in other languages.

pdf
Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models
Jiaoda Li | Duygu Ataman | Rico Sennrich
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multimodal machine translation (MMT) systems have been shown to outperform their text-only neural machine translation (NMT) counterparts when visual context is available. However, recent studies have also shown that the performance of MMT models is only marginally impacted when the associated image is replaced with an unrelated image or noise, which suggests that the visual context might not be exploited by the model at all. We hypothesize that this might be caused by the nature of the commonly used evaluation benchmark, also known as Multi30K, where the translations of image captions were prepared without actually showing the images to human translators. In this paper, we present a qualitative study that examines the role of datasets in stimulating the leverage of visual modality and we propose methods to highlight the importance of visual signals in the datasets which demonstrate improvements in reliance of models on the source images. Our findings suggest the research on effective MMT architectures is currently impaired by the lack of suitable datasets and careful consideration must be taken in creation of future MMT datasets, for which we also provide useful insights.

pdf
Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias
Jannis Vamvas | Rico Sennrich
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Lexical disambiguation is a major challenge for machine translation systems, especially if some senses of a word are trained less often than others. Identifying patterns of overgeneralization requires evaluation methods that are both reliable and scalable. We propose contrastive conditioning as a reference-free black-box method for detecting disambiguation errors. Specifically, we score the quality of a translation by conditioning on variants of the source that provide contrastive disambiguation cues. After validating our method, we apply it in a case study to perform a targeted evaluation of sequence-level knowledge distillation. By probing word sense disambiguation and translation of gendered occupation names, we show that distillation-trained models tend to overgeneralize more than other models with a comparable BLEU score. Contrastive conditioning thus highlights a side effect of distillation that is not fully captured by standard evaluation metrics. Code and data to reproduce our findings are publicly available.

pdf
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models
Biao Zhang | Ivan Titov | Rico Sennrich
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?
Chantal Amrhein | Rico Sennrich
Findings of the Association for Computational Linguistics: EMNLP 2021

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting. In our experiments, we compare how well machine translation models trained on subword- and character-level can translate these morphological phenomena. We find that learning to analyse and generate morphologically complex surface representations is still challenging, especially for non-concatenative morphological phenomena like reduplication or vowel harmony and for rare word stems. Based on our results, we recommend that novel text representation strategies be tested on a range of typologically diverse languages to minimise the risk of adopting a strategy that inadvertently disadvantages certain languages.

pdf
Edinburgh’s End-to-End Multilingual Speech Translation System for IWSLT 2021
Biao Zhang | Rico Sennrich
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)

This paper describes Edinburgh’s submissions to the IWSLT2021 multilingual speech translation (ST) task. We aim at improving multilingual translation and zero-shot performance in the constrained setting (without using any extra training data) through methods that encourage transfer learning and larger capacity modeling with advanced neural components. We build our end-to-end multilingual ST model based on Transformer, integrating techniques including adaptive speech feature selection, language-specific modeling, multi-task learning, deep and big Transformer, sparsified linear attention and root mean square layer normalization. We adopt data augmentation using machine translation models for ST which converts the zero-shot problem into a zero-resource one. Experimental results show that these methods deliver substantial improvements, surpassing the official baseline by > 15 average BLEU and outperforming our cascading system by > 2 average BLEU. Our final submission achieves competitive performance (runner up).

pdf
On Biasing Transformer Attention Towards Monotonicity
Annette Rios | Chantal Amrhein | Noëmi Aepli | Rico Sennrich
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized attention functions or pretraining. In this work, we introduce a monotonicity loss function that is compatible with standard attention mechanisms and test it on several sequence-to-sequence tasks: grapheme-to-phoneme conversion, morphological inflection, transliteration, and dialect normalization. Experiments show that we can achieve largely monotonic behavior. Performance is mixed, with larger gains on top of RNN baselines. General monotonicity does not benefit transformer multihead attention, however, we see isolated improvements when only a subset of heads is biased towards monotonic behavior.

pdf
Exploring the Importance of Source Text in Automatic Post-Editing for Context-Aware Machine Translation
Chaojun Wang | Christian Hardmeier | Rico Sennrich
Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)

Accurate translation requires document-level information, which is ignored by sentence-level machine translation. Recent work has demonstrated that document-level consistency can be improved with automatic post-editing (APE) using only target-language (TL) information. We study an extended APE model that additionally integrates source context. A human evaluation of fluency and adequacy in English–Russian translation reveals that the model with access to source context significantly outperforms monolingual APE in terms of adequacy, an effect largely ignored by automatic evaluation metrics. Our results show that TL-only modelling increases fluency without improving adequacy, demonstrating the need for conditioning on source text for automatic post-editing. They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.

pdf
Revisiting Negation in Neural Machine Translation
Gongbo Tang | Philipp Rönchen | Rico Sennrich | Joakim Nivre
Transactions of the Association for Computational Linguistics, Volume 9

In this paper, we evaluate the translation of negation both automatically and manually, in English–German (EN–DE) and English– Chinese (EN–ZH). We show that the ability of neural machine translation (NMT) models to translate negation has improved with deeper and more advanced networks, although the performance varies between language pairs and translation directions. The accuracy of manual evaluation in EN→DE, DE→EN, EN→ZH, and ZH→EN is 95.7%, 94.8%, 93.4%, and 91.7%, respectively. In addition, we show that under-translation is the most significant error type in NMT, which contrasts with the more diverse error profile previously observed for statistical machine translation. To better understand the root of the under-translation of negation, we study the model’s information flow and training data. While our information flow analysis does not reveal any deficiencies that could be used to detect or fix the under-translation of negation, we find that negation is often rephrased during training, which could make it more difficult for the model to learn a reliable link between source and target negation. We finally conduct intrinsic analysis and extrinsic probing tasks on negation, showing that NMT models can distinguish negation and non-negation tokens very well and encode a lot of information about negation in hidden states but nevertheless leave room for improvement.

2020

pdf
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
Biao Zhang | Philip Williams | Ivan Titov | Rico Sennrich
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. We identify the off-target translation issue (i.e. translating into a wrong target language) as the major source of the inferior zero-shot performance, and propose random online backtranslation to enforce the translation of unseen training language pairs. Experiments on OPUS-100 (a novel multilingual dataset with 100 languages) show that our approach substantially narrows the performance gap with bilingual models in both one-to-many and many-to-many settings, and improves zero-shot performance by ~10 BLEU, approaching conventional pivot-based methods.

pdf
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
Chaojun Wang | Rico Sennrich
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The standard training algorithm in neural machine translation (NMT) suffers from exposure bias, and alternative algorithms have been proposed to mitigate this. However, the practical impact of exposure bias is under debate. In this paper, we link exposure bias to another well-known problem in NMT, namely the tendency to generate hallucinations under domain shift. In experiments on three datasets with multiple test domains, we show that exposure bias is partially to blame for hallucinations, and that training with Minimum Risk Training, which avoids exposure bias, can mitigate this. Our analysis explains why exposure bias is more problematic under domain shift, and also links exposure bias to the beam search problem, i.e. performance deterioration with increasing beam size. Our results provide a new justification for methods that reduce exposure bias: even if they do not increase performance on in-domain test sets, they can increase model robustness to domain shift.

pdf
In Neural Machine Translation, What Does Transfer Learning Transfer?
Alham Fikri Aji | Nikolay Bogoychev | Kenneth Heafield | Rico Sennrich
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Transfer learning improves quality for low-resource machine translation, but it is unclear what exactly it transfers. We perform several ablation studies that limit information transfer, then measure the quality impact across three language pairs to gain a black-box understanding of transfer learning. Word embeddings play an important role in transfer learning, particularly if they are properly aligned. Although transfer learning can be performed without embeddings, results are sub-optimal. In contrast, transferring only the embeddings but nothing else yields catastrophic results. We then investigate diagonal alignments with auto-encoders over real languages and randomly generated sequences, finding even randomly generated sequences as parents yield noticeable but smaller gains. Finally, transfer learning can eliminate the need for a warm-up phase when training transformer models in high resource language pairs.

pdf
Domain Robustness in Neural Machine Translation
Mathias Müller | Annette Rios | Rico Sennrich
Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

pdf
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English
Gongbo Tang | Rico Sennrich | Joakim Nivre
Proceedings of the 28th International Conference on Computational Linguistics

Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this paper, we conduct an investigation into pure character-based models in the case of translating Finnish into English, including exploring the ability to learn word senses and morphological inflections and the attention mechanism. We demonstrate that word-level information is distributed over the entire character sequence rather than over a single character, and characters at different positions play different roles in learning linguistic knowledge. In addition, character-based models need more layers to encode word senses which explains why only deeper models outperform subword-based models. The attention distribution pattern shows that separators attract a lot of attention and we explore a sparse word-level attention to enforce character hidden states to capture the full word-level information. Experimental results show that the word-level attention with a single head results in 1.2 BLEU points drop.

pdf
ELITR: European Live Translator
Ondřej Bojar | Dominik Macháček | Sangeet Sagar | Otakar Smrž | Jonáš Kratochvíl | Ebrahim Ansari | Dario Franceschini | Chiara Canton | Ivan Simonini | Thai-Son Nguyen | Felix Schneider | Sebastian Stücker | Alex Waibel | Barry Haddow | Rico Sennrich | Philip Williams
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation

ELITR (European Live Translator) project aims to create a speech translation system for simultaneous subtitling of conferences and online meetings targetting up to 43 languages. The technology is tested by the Supreme Audit Office of the Czech Republic and by alfaview®, a German online conferencing system. Other project goals are to advance document-level and multilingual machine translation, automatic speech recognition, and automatic minuting.

pdf
Zero-Shot Crosslingual Sentence Simplification
Jonathan Mallinson | Rico Sennrich | Mirella Lapata
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Sentence simplification aims to make sentences easier to read and understand. Recent approaches have shown promising results with encoder-decoder models trained on large amounts of parallel data which often only exists in English. We propose a zero-shot modeling framework which transfers simplification knowledge from English to another language (for which no parallel simplification corpus exists) while generalizing across languages and tasks. A shared transformer encoder constructs language-agnostic representations, with a combination of task-specific encoder layers added on top (e.g., for translation and simplification). Empirical results using both human and automatic metrics show that our approach produces better simplifications than unsupervised and pivot-based methods.

pdf
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks
Denis Emelin | Ivan Titov | Rico Sennrich
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models’ over-reliance on dataset artifacts found in training data, specifically superficial word co-occurrences, rather than a deeper understanding of the source text. We introduce a method for the prediction of disambiguation errors based on statistical data properties, demonstrating its effectiveness across several domains and model types. Moreover, we develop a simple adversarial attack strategy that minimally perturbs sentences in order to elicit disambiguation errors to further probe the robustness of translation models. Our findings indicate that disambiguation robustness varies substantially between domains and that different models trained on the same data are vulnerable to different attacks.

pdf
On Romanization for Model Transfer Between Scripts in Neural Machine Translation
Chantal Amrhein | Rico Sennrich
Findings of the Association for Computational Linguistics: EMNLP 2020

Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.

pdf
Adaptive Feature Selection for End-to-End Speech Translation
Biao Zhang | Ivan Titov | Barry Haddow | Rico Sennrich
Findings of the Association for Computational Linguistics: EMNLP 2020

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we propose adaptive feature selection (AFS) for encoder-decoder based E2E ST. We first pre-train an ASR encoder and apply AFS to dynamically estimate the importance of each encoded speech feature to ASR. A ST encoder, stacked on top of the ASR encoder, then receives the filtered features from the (frozen) ASR encoder. We take L0DROP (Zhang et al., 2020) as the backbone for AFS, and adapt it to sparsify speech features with respect to both temporal and feature dimensions. Results on LibriSpeech EnFr and MuST-C benchmarks show that AFS facilitates learning of ST by pruning out ~84% temporal features, yielding an average translation gain of ~1.3-1.6 BLEU and a decoding speedup of ~1.4x. In particular, AFS reduces the performance gap compared to the cascade baseline, and outperforms it on LibriSpeech En-Fr with a BLEU score of 18.56 (without data augmentation).

pdf
Removing European Language Barriers with Innovative Machine Translation Technology
Dario Franceschini | Chiara Canton | Ivan Simonini | Armin Schweinfurth | Adelheid Glott | Sebastian Stüker | Thai-Son Nguyen | Felix Schneider | Thanh-Le Ha | Alex Waibel | Barry Haddow | Philip Williams | Rico Sennrich | Ondřej Bojar | Sangeet Sagar | Dominik Macháček | Otakar Smrž
Proceedings of the 1st International Workshop on Language Technology Platforms

This paper presents our progress towards deploying a versatile communication platform in the task of highly multilingual live speech translation for conferences and remote meetings live subtitling. The platform has been designed with a focus on very low latency and high flexibility while allowing research prototypes of speech and text processing tools to be easily connected, regardless of where they physically run. We outline our architecture solution and also briefly compare it with the ELG platform. Technical details are provided on the most important components and we summarize the test deployment events we ran so far.

pdf
Fast Interleaved Bidirectional Sequence Generation
Biao Zhang | Ivan Titov | Rico Sennrich
Proceedings of the Fifth Conference on Machine Translation

Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming independence between neighbouring tokens (semi-autoregressive decoding, SA), we take inspiration from bidirectional sequence generation and introduce a decoder that generates target words from the left-to-right and right-to-left directions simultaneously. We show that we can easily convert a standard architecture for unidirectional decoding into a bidirectional decoder by simply interleaving the two directions and adapting the word positions and selfattention masks. Our interleaved bidirectional decoder (IBDecoder) retains the model simplicity and training efficiency of the standard Transformer, and on five machine translation tasks and two document summarization tasks, achieves a decoding speedup of ~2x compared to autoregressive decoding with comparable quality. Notably, it outperforms left-to-right SA because the independence assumptions in IBDecoder are more felicitous. To achieve even higher speedups, we explore hybrid models where we either simultaneously predict multiple neighbouring tokens per direction, or perform multi-directional decoding by partitioning the target sequence. These methods achieve speedups to 4x–11x across different tasks at the cost of <1 BLEU or <0.5 ROUGE (on average)

pdf
Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
Annette Rios | Mathias Müller | Rico Sennrich
Proceedings of the Fifth Conference on Machine Translation

Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot translation. It is hard to predict in which settings it will be effective, and what limits performance compared to a fully supervised system. In this paper, we investigate zero-shot performance of a multilingual EN<->FR,CS,DE,FI system trained on WMT data. We find that zero-shot performance is highly unstable and can vary by more than 6 BLEU between training runs, making it difficult to reliably track improvements. We observe a bias towards copying the source in zero-shot translation, and investigate how the choice of subword segmentation affects this bias. We find that language-specific subword segmentation results in less subword copying at training time, and leads to better zero-shot performance compared to jointly trained segmentation. A recent trend in multilingual models is to not train on parallel data between all language pairs, but have a single bridge language, e.g. English. We find that this negatively affects zero-shot translation and leads to a failure mode where the model ignores the language tag and instead produces English output in zero-shot directions. We show that this bias towards English can be effectively reduced with even a small amount of parallel data in some of the non-English pairs.

2019

pdf
Samsung and University of Edinburgh’s System for the IWSLT 2019
Joanna Wetesko | Marcin Chochowski | Pawel Przybysz | Philip Williams | Roman Grundkiewicz | Rico Sennrich | Barry Haddow | Barone | Valerio Miceli | Alexandra Birch
Proceedings of the 16th International Conference on Spoken Language Translation

This paper describes the joint submission to the IWSLT 2019 English to Czech task by Samsung RD Institute, Poland, and the University of Edinburgh. Our submission was ultimately produced by combining four Transformer systems through a mixture of ensembling and reranking.

pdf
Context-Aware Monolingual Repair for Neural Machine Translation
Elena Voita | Rico Sennrich | Ivan Titov
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Modern sentence-level NMT systems often produce plausible translations of isolated sentences. However, when put in context, these translations may end up being inconsistent with each other. We propose a monolingual DocRepair model to correct inconsistencies between sentence-level translations. DocRepair performs automatic post-editing on a sequence of sentence-level translations, refining translations of sentences in context of each other. For training, the DocRepair model requires only monolingual document-level data in the target language. It is trained as a monolingual sequence-to-sequence model that maps inconsistent groups of sentences into consistent ones. The consistent groups come from the original training data; the inconsistent groups are obtained by sampling round-trip translations for each isolated sentence. We show that this approach successfully imitates inconsistencies we aim to fix: using contrastive evaluation, we show large improvements in the translation of several contextual phenomena in an English-Russian translation task, as well as improvements in the BLEU score. We also conduct a human evaluation and show a strong preference of the annotators to corrected translations over the baseline ones. Moreover, we analyze which discourse phenomena are hard to capture using monolingual data only.

pdf
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention
Biao Zhang | Ivan Titov | Rico Sennrich
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

The general trend in NLP is towards increasing model capacity and performance via deeper neural networks. However, simply stacking more layers of the popular Transformer architecture for machine translation results in poor convergence and high computational overhead. Our empirical analysis suggests that convergence is poor due to gradient vanishing caused by the interaction between residual connection and layer normalization. We propose depth-scaled initialization (DS-Init), which decreases parameter variance at the initialization stage, and reduces output variance of residual connections so as to ease gradient back-propagation through normalization layers. To address computational cost, we propose a merged attention sublayer (MAtt) which combines a simplified average-based self-attention sublayer and the encoder-decoder attention sublayer on the decoder side. Results on WMT and IWSLT translation tasks with five translation directions show that deep Transformers with DS-Init and MAtt can substantially outperform their base counterpart in terms of BLEU (+1.1 BLEU on average for 12-layer models), while matching the decoding speed of the baseline model thanks to the efficiency improvements of MAtt. Source code for reproduction will be released soon.

pdf
Encoders Help You Disambiguate Word Senses in Neural Machine Translation
Gongbo Tang | Rico Sennrich | Joakim Nivre
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Neural machine translation (NMT) has achieved new state-of-the-art performance in translating ambiguous words. However, it is still unclear which component dominates the process of disambiguation. In this paper, we explore the ability of NMT encoders and decoders to disambiguate word senses by evaluating hidden states and investigating the distributions of self-attention. We train a classifier to predict whether a translation is correct given the representation of an ambiguous noun. We find that encoder hidden states outperform word embeddings significantly which indicates that encoders adequately encode relevant information for disambiguation into hidden states. In contrast to encoders, the effect of decoder is different in models with different architectures. Moreover, the attention weights and attention entropy show that self-attention can detect ambiguous nouns and distribute more attention to the context.

pdf
The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives
Elena Voita | Rico Sennrich | Ivan Titov
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We chose the Transformers for our analysis as they have been shown effective with various tasks, including machine translation (MT), standard left-to-right language models (LM) and masked language modeling (MLM). Previous work used black-box probing tasks to show that the representations learned by the Transformer differ significantly depending on the objective. In this work, we use canonical correlation analysis and mutual information estimators to study how information flows across Transformer layers and observe that the choice of the objective determines this process. For example, as you go from bottom to top layers, information about the past in left-to-right language models gets vanished and predictions about the future get formed. In contrast, for MLM, representations initially acquire information about the context around the token, partially forgetting the token identity and producing a more generalized token representation. The token identity then gets recreated at the top MLM layers.

pdf
Revisiting Low-Resource Neural Machine Translation: A Case Study
Rico Sennrich | Biao Zhang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German–English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean–English dataset, surpassing previously reported results by 4 BLEU.

pdf
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion
Elena Voita | Rico Sennrich | Ivan Titov
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Though machine translation errors caused by the lack of context beyond one sentence have long been acknowledged, the development of context-aware NMT systems is hampered by several problems. Firstly, standard metrics are not sensitive to improvements in consistency in document-level translations. Secondly, previous work on context-aware NMT assumed that the sentence-aligned parallel data consisted of complete documents while in most practical scenarios such document-level data constitutes only a fraction of the available parallel data. To address the first issue, we perform a human study on an English-Russian subtitles dataset and identify deixis, ellipsis and lexical cohesion as three main sources of inconsistency. We then create test sets targeting these phenomena. To address the second shortcoming, we consider a set-up in which a much larger amount of sentence-level data is available compared to that aligned at the document level. We introduce a model that is suitable for this scenario and demonstrate major gains over a context-agnostic baseline on our new benchmarks without sacrificing performance as measured with BLEU.

pdf
A Lightweight Recurrent Network for Sequence Modeling
Biao Zhang | Rico Sennrich
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Recurrent networks have achieved great success on various sequential tasks with the assistance of complex recurrent units, but suffer from severe computational inefficiency due to weak parallelization. One direction to alleviate this issue is to shift heavy computations outside the recurrence. In this paper, we propose a lightweight recurrent network, or LRN. LRN uses input and forget gates to handle long-range dependencies as well as gradient vanishing and explosion, with all parameter related calculations factored outside the recurrence. The recurrence in LRN only manipulates the weight assigned to each token, tightly connecting LRN with self-attention networks. We apply LRN as a drop-in replacement of existing recurrent units in several neural sequential models. Extensive experiments on six NLP tasks show that LRN yields the best running efficiency with little or no loss in model performance.

pdf
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
Elena Voita | David Talbot | Fedor Moiseev | Rico Sennrich | Ivan Titov
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads to the overall performance of the model and analyze the roles played by them in the encoder. We find that the most important and confident heads play consistent and often linguistically-interpretable roles. When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, we observe that specialized heads are last to be pruned. Our novel pruning method removes the vast majority of heads without seriously affecting performance. For example, on the English-Russian WMT dataset, pruning 38 out of 48 encoder heads results in a drop of only 0.15 BLEU.

pdf
Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models
Gongbo Tang | Rico Sennrich | Joakim Nivre
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)

In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the source. The decoder is a standard Transformer or recurrent neural network that directly attends to embeddings via attention mechanisms. Experimental results show (1) that the attention mechanism in encoder-free models acts as a strong feature extractor, (2) that the word embeddings in encoder-free models are competitive to those in conventional models, (3) that non-contextualized source representations lead to a big performance drop, and (4) that encoder-free models have different effects on alignment quality for German-English and Chinese-English.

pdf
Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts
Denis Emelin | Ivan Titov | Rico Sennrich
Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and propagated through a deep network of hidden layers. We argue that the need to represent and propagate lexical features in each layer limits the model’s capacity for learning and representing other information relevant to the task. To alleviate this bottleneck, we introduce gated shortcut connections between the embedding layer and each subsequent layer within the encoder and decoder. This enables the model to access relevant lexical content dynamically, without expending limited resources on storing it within intermediate states. We show that the proposed modification yields consistent improvements over a baseline transformer on standard WMT translation tasks in 5 translation directions (0.9 BLEU on average) and reduces the amount of lexical information passed along the hidden layers. We furthermore evaluate different ways to integrate lexical connections into the transformer architecture and present ablation experiments exploring the effect of proposed shortcuts on model behavior.

pdf bib
Proceedings of Machine Translation Summit XVII: Research Track
Mikel Forcada | Andy Way | Barry Haddow | Rico Sennrich
Proceedings of Machine Translation Summit XVII: Research Track

2018

pdf
Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task
Philip Williams | Marcin Chochowski | Pawel Przybysz | Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the 15th International Conference on Spoken Language Translation

This paper describes the joint submission to the IWSLT 2018 Low Resource MT task by Samsung R&D Institute, Poland, and the University of Edinburgh. We focused on supplementing the very limited in-domain Basque-English training data with out-of-domain data, with synthetic data, and with data for other language pairs. We also experimented with a variety of model architectures and features, which included the development of extensions to the Nematus toolkit. Our submission was ultimately produced by a system combination in which we reranked translations from our strongest individual system using multiple weaker systems.

pdf
Sentence Compression for Arbitrary Languages via Multilingual Pivoting
Jonathan Mallinson | Rico Sennrich | Mirella Lapata
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In this paper we advocate the use of bilingual corpora which are abundantly available for training sentence compression models. Our approach borrows much of its machinery from neural machine translation and leverages bilingual pivoting: compressions are obtained by translating a source string into a foreign language and then back-translating it into the source while controlling the translation length. Our model can be trained for any language as long as a bilingual corpus is available and performs arbitrary rewrites without access to compression specific data. We release. Moss, a new parallel Multilingual Compression dataset for English, German, and French which can be used to evaluate compression models across languages and genres.

pdf
Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures
Gongbo Tang | Mathias Müller | Annette Rios | Rico Sennrich
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been speculated that this improves their ability to model long-range dependencies. However, this theoretical argument has not been tested empirically, nor have alternative explanations for their strong performance been explored in-depth. We hypothesize that the strong performance of CNNs and self-attentional networks could also be due to their ability to extract semantic features from the source text, and we evaluate RNNs, CNNs and self-attention networks on two tasks: subject-verb agreement (where capturing long-range dependencies is required) and word sense disambiguation (where semantic feature extraction is required). Our experimental results show that: 1) self-attentional networks and CNNs do not outperform RNNs in modeling subject-verb agreement over long distances; 2) self-attentional networks perform distinctly better than RNNs and CNNs on word sense disambiguation.

pdf
Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation
Samuel Läubli | Rico Sennrich | Martin Volk
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese–English news translation task. We empirically test this claim with alternative evaluation protocols, contrasting the evaluation of single sentences and entire documents. In a pairwise ranking experiment, human raters assessing adequacy and fluency show a stronger preference for human over machine translation when evaluating documents as compared to isolated sentences. Our findings emphasise the need to shift towards document-level evaluation as machine translation improves to the degree that errors which are hard or impossible to spot at the sentence-level become decisive in discriminating quality of different translation outputs.

pdf
Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method
Yutong Shao | Rico Sennrich | Bonnie Webber | Federico Fancellu
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf
Improving Machine Translation of Educational Content via Crowdsourcing
Maximiliana Behnke | Antonio Valerio Miceli Barone | Rico Sennrich | Vilelmini Sosoni | Thanasis Naskos | Eirini Takoulidou | Maria Stasimioti | Menno van Zaanen | Sheila Castilho | Federico Gaspari | Panayota Georgakopoulou | Valia Kordoni | Markus Egg | Katia Lida Kermanidis
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf
Evaluating Discourse Phenomena in Neural Machine Translation
Rachel Bawden | Rico Sennrich | Alexandra Birch | Barry Haddow
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard automatic metrics, poorly adapted to evaluating discourse phenomena. In this article, we present hand-crafted, discourse test sets, designed to test the models’ ability to exploit previous source and target sentences. We investigate the performance of recently proposed multi-encoder NMT models trained on subtitles for English to French. We also explore a novel way of exploiting context from the previous sentence. Despite gains using BLEU, multi-encoder models give limited improvement in the handling of discourse phenomena: 50% accuracy on our coreference test set and 53.5% for coherence/cohesion (compared to a non-contextual baseline of 50%). A simple strategy of decoding the concatenation of the previous and current sentence leads to good performance, and our novel strategy of multi-encoding and decoding of two sentences leads to the best performance (72.5% for coreference and 57% for coherence/cohesion), highlighting the importance of target-side context.

pdf
Context-Aware Neural Machine Translation Learns Anaphora Resolution
Elena Voita | Pavel Serdyukov | Rico Sennrich | Ivan Titov
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence. We introduce a context-aware neural machine translation model designed in such way that the flow of information from the extended context to the translation model can be controlled and analyzed. We experiment with an English-Russian subtitles dataset, and observe that much of what is captured by our model deals with improving pronoun translation. We measure correspondences between induced attention distributions and coreference relations and observe that the model implicitly captures anaphora. It is consistent with gains for sentences where pronouns need to be gendered in translation. Beside improvements in anaphoric cases, the model also improves in overall BLEU, both over its context-agnostic version (+0.7) and over simple concatenation of the context and source sentences (+0.6).

pdf
An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation
Gongbo Tang | Rico Sennrich | Joakim Nivre
Proceedings of the Third Conference on Machine Translation: Research Papers

Recent work has shown that the encoder-decoder attention mechanisms in neural machine translation (NMT) are different from the word alignment in statistical machine translation. In this paper, we focus on analyzing encoder-decoder attention mechanisms, in the case of word sense disambiguation (WSD) in NMT models. We hypothesize that attention mechanisms pay more attention to context tokens when translating ambiguous words. We explore the attention distribution patterns when translating ambiguous nouns. Counterintuitively, we find that attention mechanisms are likely to distribute more attention to the ambiguous noun itself rather than context tokens, in comparison to other nouns. We conclude that attention is not the main mechanism used by NMT models to incorporate contextual information for WSD. The experimental results suggest that NMT models learn to encode contextual information necessary for WSD in the encoder hidden states. For the attention mechanism in Transformer models, we reveal that the first few layers gradually learn to “align” source and target tokens and the last few layers learn to extract features from the related but unaligned context tokens.

pdf
A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation
Mathias Müller | Annette Rios | Elena Voita | Rico Sennrich
Proceedings of the Third Conference on Machine Translation: Research Papers

The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has seen only moderate improvements in terms of automatic evaluation metrics such as BLEU. However, metrics that quantify the overall translation quality are ill-equipped to measure gains from additional context. We argue that a different kind of evaluation is needed to assess how well models translate inter-sentential phenomena such as pronouns. This paper therefore presents a test suite of contrastive translations focused specifically on the translation of pronouns. Furthermore, we perform experiments with several context-aware models. We show that, while gains in BLEU are moderate for those systems, they outperform baselines by a large margin in terms of accuracy on our contrastive test set. Our experiments also show the effectiveness of parameter tying for multi-encoder architectures.

pdf
The University of Edinburgh’s Submissions to the WMT18 News Translation Task
Barry Haddow | Nikolay Bogoychev | Denis Emelin | Ulrich Germann | Roman Grundkiewicz | Kenneth Heafield | Antonio Valerio Miceli Barone | Rico Sennrich
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

The University of Edinburgh made submissions to all 14 language pairs in the news translation task, with strong performances in most pairs. We introduce new RNN-variant, mixed RNN/Transformer ensembles, data selection and weighting, and extensions to back-translation.

pdf
The Word Sense Disambiguation Test Suite at WMT18
Annette Rios | Mathias Müller | Rico Sennrich
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

We present a task to measure an MT system’s capability to translate ambiguous words with their correct sense according to the given context. The task is based on the German–English Word Sense Disambiguation (WSD) test set ContraWSD (Rios Gonzales et al., 2017), but it has been filtered to reduce noise, and the evaluation has been adapted to assess MT output directly rather than scoring existing translations. We evaluate all German–English submissions to the WMT’18 shared translation task, plus a number of submissions from previous years, and find that performance on the task has markedly improved compared to the 2016 WMT submissions (81%→93% accuracy on the WSD task). We also find that the unsupervised submissions to the task have a low WSD capability, and predominantly translate ambiguous source words with the same sense.

2017

pdf
The Samsung and University of Edinburgh’s submission to IWSLT17
Pawel Przybysz | Marcin Chochowski | Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the 14th International Conference on Spoken Language Translation

This paper describes the joint submission of Samsung Research and Development, Warsaw, Poland and the University of Edinburgh team to the IWSLT MT task for TED talks. We took part in two translation directions, en-de and de-en. We also participated in the en-de and de-en lectures SLT task. The models have been trained with an attentional encoder-decoder model using the BiDeep model in Nematus. We filtered the training data to reduce the problem of noisy data, and we use back-translated monolingual data for domain-adaptation. We demonstrate the effectiveness of the different techniques that we applied via ablation studies. Our submission system outperforms our baseline, and last year’s University of Edinburgh submission to IWSLT, by more than 5 BLEU.

pdf
A Comparative Quality Evaluation of PBSMT and NMT using Professional Translators
Sheila Castilho | Joss Moorkens | Federico Gaspari | Rico Sennrich | Vilelmini Sosoni | Panayota Georgakopoulou | Pintu Lohar | Andy Way | Antonio Valerio Miceli-Barone | Maria Gialama
Proceedings of Machine Translation Summit XVI: Research Track

pdf
Regularization techniques for fine-tuning in neural machine translation
Antonio Valerio Miceli Barone | Barry Haddow | Ulrich Germann | Rico Sennrich
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major challenge. We investigate a number of techniques to reduce overfitting and improve transfer learning, including regularization techniques such as dropout and L2-regularization towards an out-of-domain prior. In addition, we introduce tuneout, a novel regularization technique inspired by dropout. We apply these techniques, alone and in combination, to neural machine translation, obtaining improvements on IWSLT datasets for English→German and English→Russian. We also investigate the amounts of in-domain training data needed for domain adaptation in NMT, and find a logarithmic relationship between the amount of training data and gain in BLEU score.

pdf
Image Pivoting for Learning Multilingual Multimodal Representations
Spandana Gella | Rico Sennrich | Frank Keller | Mirella Lapata
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model learns a common representation for images and their descriptions in two different languages (which need not be parallel) by considering the image as a pivot between two languages. We introduce a new pairwise ranking loss function which can handle both symmetric and asymmetric similarity between the two modalities. We evaluate our models on image-description ranking for German and English, and on semantic textual similarity of image descriptions in English. In both cases we achieve state-of-the-art performance.

pdf
Paraphrasing Revisited with Neural Machine Translation
Jonathan Mallinson | Rico Sennrich | Mirella Lapata
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

Recognizing and generating paraphrases is an important component in many natural language processing applications. A well-established technique for automatically extracting paraphrases leverages bilingual corpora to find meaning-equivalent phrases in a single language by “pivoting” over a shared translation in another language. In this paper we revisit bilingual pivoting in the context of neural machine translation and present a paraphrasing model based purely on neural networks. Our model represents paraphrases in a continuous space, estimates the degree of semantic relatedness between text segments of arbitrary length, and generates candidate paraphrases for any source input. Experimental results across tasks and datasets show that neural paraphrases outperform those obtained with conventional phrase-based pivoting approaches.

pdf
How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs
Rico Sennrich
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Analysing translation quality in regards to specific linguistic phenomena has historically been difficult and time-consuming. Neural machine translation has the attractive property that it can produce scores for arbitrary translations, and we propose a novel method to assess how well NMT systems model specific linguistic phenomena such as agreement over long distances, the production of novel words, and the faithful translation of polarity. The core idea is that we measure whether a reference translation is more probable under a NMT model than a contrastive translation which introduces a specific type of error. We present LingEval97, a large-scale data set of 97000 contrastive translation pairs based on the WMT English->German translation task, with errors automatically created with simple rules. We report results for a number of systems, and find that recently introduced character-level NMT systems perform better at transliteration than models with byte-pair encoding (BPE) segmentation, but perform more poorly at morphosyntactic agreement, and translating discontiguous units of meaning.

pdf
Nematus: a Toolkit for Neural Machine Translation
Rico Sennrich | Orhan Firat | Kyunghyun Cho | Alexandra Birch | Barry Haddow | Julian Hitschler | Marcin Junczys-Dowmunt | Samuel Läubli | Antonio Valerio Miceli Barone | Jozef Mokry | Maria Nădejde
Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics

We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and has been used to train systems for production environments.

pdf
The SUMMA Platform Prototype
Renars Liepins | Ulrich Germann | Guntis Barzdins | Alexandra Birch | Steve Renals | Susanne Weber | Peggy van der Kreeft | Hervé Bourlard | João Prieto | Ondřej Klejch | Peter Bell | Alexandros Lazaridis | Alfonso Mendes | Sebastian Riedel | Mariana S. C. Almeida | Pedro Balage | Shay B. Cohen | Tomasz Dwojak | Philip N. Garner | Andreas Giefer | Marcin Junczys-Dowmunt | Hina Imran | David Nogueira | Ahmed Ali | Sebastião Miranda | Andrei Popescu-Belis | Lesly Miculicich Werlen | Nikos Papasarantopoulos | Abiola Obamuyide | Clive Jones | Fahim Dalvi | Andreas Vlachos | Yang Wang | Sibo Tong | Rico Sennrich | Nikolaos Pappas | Shashi Narayan | Marco Damonte | Nadir Durrani | Sameer Khurana | Ahmed Abdelali | Hassan Sajjad | Stephan Vogel | David Sheppey | Chris Hernon | Jeff Mitchell
Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadcast media, machine translation, automated tagging and classification of named entities, semantic parsing to detect relationships between entities, and automatic construction / augmentation of factual knowledge bases. Implemented on the Docker platform, it can easily be deployed, customised, and scaled to large volumes of incoming media streams.

pdf bib
Practical Neural Machine Translation
Rico Sennrich | Barry Haddow
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts

Neural Machine Translation (NMT) has achieved new breakthroughs in machine translation in recent years. It has dominated recent shared translation tasks in machine translation research, and is also being quickly adopted in industry. The technical differences between NMT and the previously dominant phrase-based statistical approach require that practictioners learn new best practices for building MT systems, ranging from different hardware requirements, new techniques for handling rare words and monolingual data, to new opportunities in continued learning and domain adaptation.This tutorial is aimed at researchers and users of machine translation interested in working with NMT. The tutorial will cover a basic theoretical introduction to NMT, discuss the components of state-of-the-art systems, and provide practical advice for building NMT systems.

pdf
A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation
Antonio Valerio Miceli Barone | Rico Sennrich
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Automated documentation of programming source code and automated code generation from natural language are challenging tasks of both practical and scientific interest. Progress in these areas has been limited by the low availability of parallel corpora of code and natural language descriptions, which tend to be small and constrained to specific domains. In this work we introduce a large and diverse parallel corpus of a hundred thousands Python functions with their documentation strings (“docstrings”) generated by scraping open source repositories on GitHub. We describe baseline results for the code documentation and code generation tasks obtained by neural machine translation. We also experiment with data augmentation techniques to further increase the amount of training data. We release our datasets and processing scripts in order to stimulate research in these areas.

pdf bib
Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings
Annette Rios Gonzales | Laura Mascarell | Rico Sennrich
Proceedings of the Second Conference on Machine Translation

pdf
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Maria Nădejde | Siva Reddy | Rico Sennrich | Tomasz Dwojak | Marcin Junczys-Dowmunt | Philipp Koehn | Alexandra Birch
Proceedings of the Second Conference on Machine Translation

pdf
Deep architectures for Neural Machine Translation
Antonio Valerio Miceli Barone | Jindřich Helcl | Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the Second Conference on Machine Translation

pdf
The University of Edinburgh’s Neural MT Systems for WMT17
Rico Sennrich | Alexandra Birch | Anna Currey | Ulrich Germann | Barry Haddow | Kenneth Heafield | Antonio Valerio Miceli Barone | Philip Williams
Proceedings of the Second Conference on Machine Translation

2016

pdf
TraMOOC (Translation for Massive Open Online Courses): providing reliable MT for MOOCs
Valia Kordoni | Lexi Birch | Ioana Buliga | Kostadin Cholakov | Markus Egg | Federico Gaspari | Yota Georgakopolou | Maria Gialama | Iris Hendrickx | Mitja Jermol | Katia Kermanidis | Joss Moorkens | Davor Orlic | Michael Papadopoulos | Maja Popović | Rico Sennrich | Vilelmini Sosoni | Dimitrios Tsoumakos | Antal van den Bosch | Menno van Zaanen | Andy Way
Proceedings of the 19th Annual Conference of the European Association for Machine Translation: Projects/Products

pdf
Controlling Politeness in Neural Machine Translation via Side Constraints
Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf
Improving Neural Machine Translation Models with Monolingual Data
Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Neural Machine Translation of Rare Words with Subword Units
Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Linguistic Input Features Improve Neural Machine Translation
Rico Sennrich | Barry Haddow
Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers

pdf
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
Marcin Junczys-Dowmunt | Tomasz Dwojak | Rico Sennrich
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf
The QT21/HimL Combined Machine Translation System
Jan-Thorsten Peter | Tamer Alkhouli | Hermann Ney | Matthias Huck | Fabienne Braune | Alexander Fraser | Aleš Tamchyna | Ondřej Bojar | Barry Haddow | Rico Sennrich | Frédéric Blain | Lucia Specia | Jan Niehues | Alex Waibel | Alexandre Allauzen | Lauriane Aufrant | Franck Burlot | Elena Knyazeva | Thomas Lavergne | François Yvon | Mārcis Pinnis | Stella Frank
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf
Edinburgh Neural Machine Translation Systems for WMT 16
Rico Sennrich | Barry Haddow | Alexandra Birch
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf
Edinburgh’s Statistical Machine Translation Systems for WMT16
Philip Williams | Rico Sennrich | Maria Nădejde | Matthias Huck | Barry Haddow | Ondřej Bojar
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

2015

pdf
A Joint Dependency Model of Morphological and Syntactic Structure for Statistical Machine Translation
Rico Sennrich | Barry Haddow
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf
Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation
Rico Sennrich
Transactions of the Association for Computational Linguistics, Volume 3

The role of language models in SMT is to promote fluent translation output, but traditional n-gram language models are unable to capture fluency phenomena between distant words, such as some morphological agreement phenomena, subcategorisation, and syntactic collocations with string-level gaps. Syntactic language models have the potential to fill this modelling gap. We propose a language model for dependency structures that is relational rather than configurational and thus particularly suited for languages with a (relatively) free word order. It is trainable with Neural Networks, and not only improves over standard n-gram language models, but also outperforms related syntactic language models. We empirically demonstrate its effectiveness in terms of perplexity and as a feature function in string-to-tree SMT from English to German and Russian. We also show that using a syntactic evaluation metric to tune the log-linear parameters of an SMT system further increases translation quality when coupled with a syntactic language model.

pdf
Edinburgh’s Syntax-Based Systems at WMT 2015
Philip Williams | Rico Sennrich | Maria Nadejde | Matthias Huck | Philipp Koehn
Proceedings of the Tenth Workshop on Statistical Machine Translation

2014

pdf
Handling technical OOVs in SMT
Mark Fishel | Rico Sennrich
Proceedings of the 17th Annual Conference of the European Association for Machine Translation

pdf
Zmorge: A German Morphological Lexicon Extracted from Wiktionary
Rico Sennrich | Beat Kunz
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

We describe a method to automatically extract a German lexicon from Wiktionary that is compatible with the finite-state morphological grammar SMOR. The main advantage of the resulting lexicon over existing lexica for SMOR is that it is open and permissively licensed. A recall-oriented evaluation shows that a morphological analyser built with our lexicon has comparable coverage compared to existing lexica, and continues to improve as Wiktionary grows. We also describe modifications to the SMOR grammar that result in a more conventional lemmatisation of words.

pdf
EU-BRIDGE MT: Combined Machine Translation
Markus Freitag | Stephan Peitz | Joern Wuebker | Hermann Ney | Matthias Huck | Rico Sennrich | Nadir Durrani | Maria Nadejde | Philip Williams | Philipp Koehn | Teresa Herrmann | Eunah Cho | Alex Waibel
Proceedings of the Ninth Workshop on Statistical Machine Translation

pdf
Edinburgh’s Syntax-Based Systems at WMT 2014
Philip Williams | Rico Sennrich | Maria Nadejde | Matthias Huck | Eva Hasler | Philipp Koehn
Proceedings of the Ninth Workshop on Statistical Machine Translation

pdf
A CYK+ Variant for SCFG Decoding Without a Dot Chart
Rico Sennrich
Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation

2013

pdf bib
Promoting Flexible Translations in Statistical Machine Translation
Rico Sennrich
Proceedings of Machine Translation Summit XIV: Posters

pdf
A Multi-Domain Translation Model Framework for Statistical Machine Translation
Rico Sennrich | Holger Schwenk | Walid Aransa
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Exploiting Synergies Between Open Resources for German Dependency Parsing, POS-tagging, and Morphological Analysis
Rico Sennrich | Martin Volk | Gerold Schneider
Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013

2012

pdf
Mixture-Modeling with Unsupervised Clusters for Domain Adaptation in Statistical Machine Translation
Rico Sennrich
Proceedings of the 16th Annual Conference of the European Association for Machine Translation

pdf
Perplexity Minimization for Translation Model Domain Adaptation in Statistical Machine Translation
Rico Sennrich
Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

pdf
TerrorCat: a Translation Error Categorization-based MT Quality Metric
Mark Fishel | Rico Sennrich | Maja Popović | Ondřej Bojar
Proceedings of the Seventh Workshop on Statistical Machine Translation

2011

pdf
Combining Multi-Engine Machine Translation and Online Learning through Dynamic Phrase Tables
Rico Sennrich
Proceedings of the 15th Annual Conference of the European Association for Machine Translation

pdf
The UZH System Combination System for WMT 2011
Rico Sennrich
Proceedings of the Sixth Workshop on Statistical Machine Translation

pdf
Iterative, MT-based Sentence Alignment of Parallel Texts
Rico Sennrich | Martin Volk
Proceedings of the 18th Nordic Conference of Computational Linguistics (NODALIDA 2011)

pdf
Disambiguation of English Contractions for Machine Translation of TV Subtitles
Martin Volk | Rico Sennrich
Proceedings of the 18th Nordic Conference of Computational Linguistics (NODALIDA 2011)

2010

pdf
MT-based Sentence Alignment for OCR-generated Parallel Texts
Rico Sennrich | Martin Volk
Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers

The performance of current sentence alignment tools varies according to the to-be-aligned texts. We have found existing tools unsuitable for hard-to-align parallel texts and describe an alternative alignment algorithm. The basic idea is to use machine translations of a text and BLEU as a similarity score to find reliable alignments which are used as anchor points. The gaps between these anchor points are then filled using BLEU-based and length-based heuristics. We show that this approach outperforms state-of-the-art algorithms in our alignment task, and that this improvement in alignment quality translates into better SMT performance. Furthermore, we show that even length-based alignment algorithms profit from having a machine translation as a point of comparison.

pdf
Machine Translation of TV Subtitles for Large Scale Production
Martin Volk | Rico Sennrich | Christian Hardmeier | Frida Tidström
Proceedings of the Second Joint EM+/CNGL Workshop: Bringing MT to the User: Research on Integrating MT in the Translation Industry

This paper describes our work on building and employing Statistical Machine Translation systems for TV subtitles in Scandinavia. We have built translation systems for Danish, English, Norwegian and Swedish. They are used in daily subtitle production and translate large volumes. As an example we report on our evaluation results for three TV genres. We discuss our lessons learned in the system development process which shed interesting light on the practical use of Machine Translation technology.
Search
Co-authors