Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. Therefore, translation has to start with an incomplete source text, which is read progressively, creating the need for anticipation. In this talk I will present work where we seek to understand whether the addition of visual information can compensate for the missing source context. We analyse the impact of different multimodal approaches and visual features on state-of-the-art SiMT frameworks, including fixed and dynamic policy approaches using reinforcement learning. Our results show that visual context is helpful and that visually-grounded models based on explicit object region information perform the best. Our qualitative analysis illustrates cases where only the multimodal systems are able to translate correctly from English into gender-marked languages, as well as deal with differences in word order, such as adjective-noun placement between English and French.
Quality estimation aims to measure the quality of translated content without access to a reference translation. This is crucial for machine translation systems in real-world scenarios where high-quality translation is needed. While many approaches exist for quality estimation, they are based on supervised machine learning requiring costly human labelled data. As an alternative, we propose a technique that does not rely on examples from human-annotators and instead uses synthetic training data. We train off-the-shelf architectures for supervised quality estimation on our synthetic data and show that the resulting models achieve comparable performance to models trained on human-annotated data, both for sentence and word-level prediction.
Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and visual pre-training methods. In this paper, we combine these two approaches to learn visually-grounded cross-lingual representations. Specifically, we extend the translation language modelling (Lample and Conneau, 2019) with masked region classification and perform pre-training with three-way parallel vision & language corpora. We show that when fine-tuned for multimodal machine translation, these models obtain state-of-the-art performance. We also provide qualitative insights into the usefulness of the learned grounded representations.
Reinforcement Learning (RL) is a powerful framework to address the discrepancy between loss functions used during training and the final evaluation metrics to be used at test time. When applied to neural Machine Translation (MT), it minimises the mismatch between the cross-entropy loss and non-differentiable evaluation metrics like BLEU. However, the suitability of these metrics as reward function at training time is questionable: they tend to be sparse and biased towards the specific words used in the reference texts. We propose to address this problem by making models less reliant on such metrics in two ways: (a) with an entropy-regularised RL method that does not only maximise a reward function but also explore the action space to avoid peaky distributions; (b) with a novel RL method that explores a dynamic unsupervised reward function to balance between exploration and exploitation. We base our proposals on the Soft Actor-Critic (SAC) framework, adapting the off-policy maximum entropy model for language generation applications such as MT. We demonstrate that SAC with BLEU reward tends to overfit less to the training data and performs better on out-of-domain data. We also show that our dynamic unsupervised reward can lead to better translation of ambiguous words.
This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to support this process by providing additional (visual) contextual information which may be available before the textual input is produced. For that, we propose a multimodal approach to simultaneous machine translation using reinforcement learning, with strategies to integrate visual and textual information in both the agent and the environment. We provide an exploration on how different types of visual information and integration strategies affect the quality and latency of simultaneous translation models, and demonstrate that visual cues lead to higher quality while keeping the latency low.
In this paper, we propose a definition and taxonomy of various types of non-standard textual content – generally referred to as “noise” – in Natural Language Processing (NLP). While data pre-processing is undoubtedly important in NLP, especially when dealing with user-generated content, a broader understanding of different sources of noise and how to deal with them is an aspect that has been largely neglected. We provide a comprehensive list of potential sources of noise, categorise and describe them, and show the impact of a subset of standard pre-processing strategies on different tasks. Our main goal is to raise awareness of non-standard content – which should not always be considered as “noise” – and of the need for careful, task-dependent pre-processing. This is an alternative to blanket, all-encompassing solutions generally applied by researchers through “standard” pre-processing pipelines. The intention is for this categorisation to serve as a point of reference to support NLP researchers in devising strategies to clean, normalise or embrace non-standard content.
Neural Machine Translation models are sensitive to noise in the input texts, such as misspelled words and ungrammatical constructions. Existing robustness techniques generally fail when faced with unseen types of noise and their performance degrades on clean texts. In this paper, we focus on three types of realistic noise that are commonly generated by humans and introduce the idea of visual context to improve translation robustness for noisy texts. In addition, we describe a novel error correction training regime that can be used as an auxiliary task to further improve translation robustness. Experiments on English-French and English-German translation show that both multimodal and error correction components improve model robustness to noisy texts, while still retaining translation quality on clean texts.
Abstract In order to simplify sentences, several rewriting operations can be performed, such as replacing complex words per simpler synonyms, deleting unnecessary information, and splitting long sentences. Despite this multi-operation nature, evaluation of automatic simplification systems relies on metrics that moderately correlate with human judgments on the simplicity achieved by executing specific operations (e.g., simplicity gain based on lexical replacements). In this article, we investigate how well existing metrics can assess sentence-level simplifications where multiple operations may have been applied and which, therefore, require more general simplicity judgments. For that, we first collect a new and more reliable data set for evaluating the correlation of metrics and human judgments of overall simplicity. Second, we conduct the first meta-evaluation of automatic metrics in Text Simplification, using our new data set (and other existing data) to analyze the variation of the correlation between metrics’ scores and human judgments across three dimensions: the perceived simplicity level, the system type, and the set of references used for computation. We show that these three aspects affect the correlations and, in particular, highlight the limitations of commonly used operation-specific metrics. Finally, based on our findings, we propose a set of recommendations for automatic evaluation of multi-operation simplifications, suggesting which metrics to compute and how to interpret their scores.
Translating text into a language unknown to the text’s author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility. We demonstrate this by showing three ways in which user confidence in the outbound translation, as well as its overall final quality, can be affected: backward translation, quality estimation (with alignment) and source paraphrasing. In this paper, we describe an experiment on outbound translation from English to Czech and Estonian. We examine the effects of each proposed feedback module and further focus on how the quality of machine translation systems influence these findings and the user perception of success. We show that backward translation feedback has a mixed effect on the whole process: it increases user confidence in the produced translation, but not the objective quality.
Machine translation (MT) is currently evaluated in one of two ways: in a monolingual fashion, by comparison with the system output to one or more human reference translations, or in a trained crosslingual fashion, by building a supervised model to predict quality scores from human-labeled data. In this paper, we propose a more cost-effective, yet well performing unsupervised alternative SentSim: relying on strong pretrained multilingual word and sentence representations, we directly compare the source with the machine translated sentence, thus avoiding the need for both reference translations and labelled training data. The metric builds on state-of-the-art embedding-based approaches – namely BERTScore and Word Mover’s Distance – by incorporating a notion of sentence semantic similarity. By doing so, it achieves better correlation with human scores on different datasets. We show that it outperforms these and other metrics in the standard monolingual setting (MT-reference translation), a well as in the source-MT bilingual setting, where it performs on par with glass-box approaches to quality estimation that rely on MT model information.
In modern computer-aided translation workflows, Machine Translation (MT) systems are used to produce a draft that is then checked and edited where needed by human translators. In this scenario, a Quality Estimation (QE) tool can be used to score MT outputs, and a threshold on the QE scores can be applied to decide whether an MT output can be used as-is or requires human post-edition. While this could reduce cost and turnaround times, it could harm translation quality, as QE models are not 100% accurate. In the framework of the APE-QUEST project (Automated Post-Editing and Quality Estimation), we set up a case-study on the trade-off between speed, cost and quality, investigating the benefits of QE models in a real-world scenario, where we rely on end-user acceptability as quality metric. Using data in the public administration domain for English-Dutch and English-French, we experimented with two use cases: assimilation and dissemination. Results shed some light on how QE scores can be explored to establish thresholds that suit each use case and target language, and demonstrate the potential benefits of adding QE to a translation workflow.
We present BERTGen, a novel, generative, decoder-only model which extends BERT by fusing multimodal and multilingual pre-trained models VL-BERT and M-BERT, respectively. BERTGen is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multi-task setting. With a comprehensive set of evaluations, we show that BERTGen outperforms many strong baselines across the tasks explored. We also show BERTGen’s ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGen substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.
Most current quality estimation (QE) models for machine translation are trained and evaluated in a static setting where training and test data are assumed to be from a fixed distribution. However, in real-life settings, the test data that a deployed QE model would be exposed to may differ from its training data. In particular, training samples are often labelled by one or a small set of annotators, whose perceptions of translation quality and needs may differ substantially from those of end-users, who will employ predictions in practice. To address this challenge, we propose an online Bayesian meta-learning framework for the continuous training of QE models that is able to adapt them to the needs of different users, while being robust to distributional shifts in training and test data. Experiments on data with varying number of users and language characteristics validate the effectiveness of the proposed approach.
Sentence-level Quality estimation (QE) of machine translation is traditionally formulated as a regression task, and the performance of QE models is typically measured by Pearson correlation with human labels. Recent QE models have achieved previously-unseen levels of correlation with human judgments, but they rely on large multilingual contextualized language models that are computationally expensive and make them infeasible for real-world applications. In this work, we evaluate several model compression techniques for QE and find that, despite their popularity in other NLP tasks, they lead to poor performance in this regression setting. We observe that a full model parameterization is required to achieve SoTA results in a regression task. However, we argue that the level of expressiveness of a model in a continuous range is unnecessary given the downstream applications of QE, and show that reframing QE as a classification problem and evaluating QE models using classification metrics would better reflect their actual performance in real-world applications.
We propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement learning. Here we formulate simultaneous translation as a structural sequence-to-sequence learning problem. A latent variable is introduced to model read or translate actions at every time step, which is then integrated out to consider all the possible translation policies. A re-parameterised Poisson prior is used to regularise the policies which allows the model to explicitly balance translation quality and latency. The experiments demonstrate the effectiveness and robustness of the generative framework, which achieves the best BLEU scores given different average translation latencies on benchmark datasets.
We introduce deepQuest-py, a framework for training and evaluation of large and light-weight models for Quality Estimation (QE). deepQuest-py provides access to (1) state-of-the-art models based on pre-trained Transformers for sentence-level and word-level QE; (2) light-weight and efficient sentence-level models implemented via knowledge distillation; and (3) a web interface for testing models and visualising their predictions. deepQuest-py is available at https://github.com/sheffieldnlp/deepQuest-py under a CC BY-NC-SA licence.
Despite peer-reviewing being an essential component of academia since the 1600s, it has repeatedly received criticisms for lack of transparency and consistency. We posit that recent work in machine learning and explainable AI provide tools that enable insights into the decisions from a given peer-review process. We start by simulating the peer-review process using an ML classifier and extracting global explanations in the form of linguistic features that affect the acceptance of a scientific paper for publication on an open peer-review dataset. Second, since such global explanations do not justify causal interpretations, we propose a methodology for detecting confounding effects in natural language and generating explanations, disentangled from textual confounders, in the form of lexicons. Our proposed linguistic explanation methodology indicates the following on a case dataset of ICLR submissions: a) the organising committee follows, for the most part, the recommendations of reviewers, and b) the paper’s main characteristics that led to reviewers recommending acceptance for publication are originality, clarity and substance.
The societal issue of digital hostility has previously attracted a lot of attention. The topic counts an ample body of literature, yet remains prominent and challenging as ever due to its subjective nature. We posit that a better understanding of this problem will require the use of causal inference frameworks. This survey summarises the relevant research that revolves around estimations of causal effects related to online hate speech. Initially, we provide an argumentation as to why re-establishing the exploration of hate speech in causal terms is of the essence. Following that, we give an overview of the leading studies classified with respect to the direction of their outcomes, as well as an outline of all related research, and a summary of open research problems that can influence future work on the topic.
Current Machine Translation (MT) systems achieve very good results on a growing variety of language pairs and datasets. However, they are known to produce fluent translation outputs that can contain important meaning errors, thus undermining their reliability in practice. Quality Estimation (QE) is the task of automatically assessing the performance of MT systems at test time. Thus, in order to be useful, QE systems should be able to detect such errors. However, this ability is yet to be tested in the current evaluation practices, where QE systems are assessed only in terms of their correlation with human judgements. In this work, we bridge this gap by proposing a general methodology for adversarial testing of QE for MT. First, we show that despite a high correlation with human judgements achieved by the recent SOTA, certain types of meaning errors are still problematic for QE to detect. Second, we show that on average, the ability of a given model to discriminate between meaning-preserving and meaning-altering perturbations is predictive of its overall performance, thus potentially allowing for comparing QE systems without relying on manual quality annotation.
We report the results of the WMT 2021 shared task on Quality Estimation, where the challenge is to predict the quality of the output of neural machine translation systems at the word and sentence levels. This edition focused on two main novel additions: (i) prediction for unseen languages, i.e. zero-shot settings, and (ii) prediction of sentences with catastrophic errors. In addition, new data was released for a number of languages, especially post-edited data. Participating teams from 19 institutions submitted altogether 1263 systems to different task variants and language pairs.
This paper presents Imperial College London’s submissions to the WMT21 Quality Estimation (QE) Shared Task 3: Critical Error Detection. Our approach builds on cross-lingual pre-trained representations in a sequence classification model. We further improve the base classifier by (i) adding a weighted sampler to deal with unbalanced data and (ii) introducing feature engineering, where features related to toxicity, named-entities and sentiment, which are potentially indicative of critical errors, are extracted using existing tools and integrated to the model in different ways. We train models with one type of feature at a time and ensemble those models that improve over the base classifier on the development (dev) set. Our official submissions achieve very competitive results, ranking second for three out of four language pairs.
Most current quality estimation (QE) models for machine translation are trained and evaluated in a fully supervised setting requiring significant quantities of labelled training data. However, obtaining labelled data can be both expensive and time-consuming. In addition, the test data that a deployed QE model would be exposed to may differ from its training data in significant ways. In particular, training samples are often labelled by one or a small set of annotators, whose perceptions of translation quality and needs may differ substantially from those of end-users, who will employ predictions in practice. Thus, it is desirable to be able to adapt QE models efficiently to new user data with limited supervision data. To address these challenges, we propose a Bayesian meta-learning approach for adapting QE models to the needs and preferences of each user with limited supervision. To enhance performance, we further propose an extension to a state-of-the-art Bayesian meta-learning approach which utilizes a matrix-valued kernel for Bayesian meta-learning of quality estimation. Experiments on data with varying number of users and language characteristics demonstrates that the proposed Bayesian meta-learning approach delivers improved predictive performance in both limited and full supervision settings.
Predicting the quality of machine translation has traditionally been addressed with language-specific models, under the assumption that the quality label distribution or linguistic features exhibit traits that are not shared across languages. An obvious disadvantage of this approach is the need for labelled data for each given language pair. We challenge this assumption by exploring different approaches to multilingual Quality Estimation (QE), including using scores from translation models. We show that these outperform single-language models, particularly in less balanced quality label distributions and low-resource settings. In the extreme case of zero-shot QE, we show that it is possible to accurately predict quality for any given new language from models trained on other languages. Our findings indicate that state-of-the-art neural QE models based on powerful pre-trained representations generalise well across languages, making them more applicable in real-world settings.
Since obtaining a perfect training dataset (i.e., a dataset which is considerably large, unbiased, and well-representative of unseen cases) is hardly possible, many real-world text classifiers are trained on the available, yet imperfect, datasets. These classifiers are thus likely to have undesirable properties. For instance, they may have biases against some sub-populations or may not work effectively in the wild due to overfitting. In this paper, we propose FIND – a framework which enables humans to debug deep learning text classifiers by disabling irrelevant hidden features. Experiments show that by using FIND, humans can improve CNN text classifiers which were trained under different types of imperfect datasets (including datasets with biases and datasets with dissimilar train-test distributions).
Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is read progressively, creating the need for anticipation. In this paper, we seek to understand whether the addition of visual information can compensate for the missing source context. To this end, we analyse the impact of different multimodal approaches and visual features on state-of-the-art SiMT frameworks. Our results show that visual context is helpful and that visually-grounded models based on explicit object region information are much better than commonly used global features, reaching up to 3 BLEU points improvement under low latency scenarios. Our qualitative analysis illustrates cases where only the multimodal systems are able to translate correctly from English into gender-marked languages, as well as deal with differences in word order, such as adjective-noun placement between English and French.
Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations can be performed such as replacement, reordering, and splitting. Executing these transformations while keeping sentences grammatical, preserving their main idea, and generating simpler output, is a challenging and still far from solved problem. In this article, we survey research on SS, focusing on approaches that attempt to learn how to simplify using corpora of aligned original-simplified sentence pairs in English, which is the dominant paradigm nowadays. We also include a benchmark of different approaches on common data sets so as to compare them and highlight their strengths and limitations. We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments.
We report the findings of the second edition of the shared task on improving robustness in Machine Translation (MT). The task aims to test current machine translation systems in their ability to handle challenges facing MT models to be deployed in the real world, including domain diversity and non-standard texts common in user generated content, especially in social media. We cover two language pairs – English-German and English-Japanese and provide test sets in zero-shot and few-shot variants. Participating systems are evaluated both automatically and manually, with an additional human evaluation for ”catastrophic errors”. We received 59 submissions by 11 participating teams from a variety of types of institutions.
We report the results of the WMT20 shared task on Quality Estimation, where the challenge is to predict the quality of the output of neural machine translation systems at the word, sentence and document levels. This edition included new data with open domain texts, direct assessment annotations, and multiple language pairs: English-German, English-Chinese, Russian-English, Romanian-English, Estonian-English, Sinhala-English and Nepali-English data for the sentence-level subtasks, English-German and English-Chinese for the word-level subtask, and English-French data for the document-level subtask. In addition, we made neural machine translation models available to participants. 19 participating teams from 27 institutions submitted altogether 1374 systems to different task variants and language pairs.
This paper presents our submission to the WMT2020 Shared Task on Quality Estimation (QE). We participate in Task and Task 2 focusing on sentence-level prediction. We explore (a) a black-box approach to QE based on pre-trained representations; and (b) glass-box approaches that leverage various indicators that can be extracted from the neural MT systems. In addition to training a feature-based regression model using glass-box quality indicators, we also test whether they can be used to predict MT quality directly with no supervision. We assess our systems in a multi-lingual setting and show that both types of approaches generalise well across languages. Our black-box QE models tied for the winning submission in four out of seven language pairs inTask 1, thus demonstrating very strong performance. The glass-box approaches also performed competitively, representing a light-weight alternative to the neural-based models.
Approaches to Quality Estimation (QE) of machine translation have shown promising results at predicting quality scores for translated sentences. However, QE models are often trained on noisy approximations of quality annotations derived from the proportion of post-edited words in translated sentences instead of direct human annotations of translation errors. The latter is a more reliable ground-truth but more expensive to obtain. In this paper, we present the first attempt to model the task of predicting the proportion of actual translation errors in a sentence while minimising the need for direct human annotation. For that purpose, we use transfer-learning to leverage large scale noisy annotations and small sets of high-fidelity human annotated translation errors to train QE models. Experiments on four language pairs and translations obtained by statistical and neural models show consistent gains over strong baselines.
Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time. Existing approaches require large amounts of expert annotated data, computation, and time for training. As an alternative, we devise an unsupervised approach to QE where no training or access to additional resources besides the MT system itself is required. Different from most of the current work that treats the MT system as a black box, we explore useful information that can be extracted from the MT system as a by-product of translation. By utilizing methods for uncertainty quantification, we achieve very good correlation with human judgments of quality, rivaling state-of-the-art supervised QE models. To evaluate our approach we collect the first dataset that enables work on both black-box and glass-box approaches to QE.
Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics remain as the de facto metrics to evaluate tasks such as image captioning and machine translation, despite their known limitations. This is partly due to ease of use, and partly because researchers expect to see them and know how to interpret them. In this paper, we urge the community for more careful consideration of how they automatically evaluate their models by demonstrating important failure cases on multiple datasets, language pairs and tasks. Our experiments show that metrics (i) usually prefer system outputs to human-authored texts, (ii) can be insensitive to correct translations of rare words, (iii) can yield surprisingly high scores when given a single sentence as system output for the entire test set.
This paper describes our submission to the 2020 Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE). This task focuses on improving the ability of neural MT systems to generate diverse translations. Our submission explores various methods, including N-best translation, Monte Carlo dropout, Diverse Beam Search, Mixture of Experts, Ensembling, and Lexical Substitution. Our main submission is based on the integration of multiple translations from multiple methods using Consensus Voting. Experiments show that the proposed approach achieves a considerable degree of diversity without introducing noisy translations. Our final submission achieves a 0.5510 weighted F1 score on the blind test set for the English-Portuguese track.
We introduce a machine translation dataset for three pairs of languages in the legal domain with post-edited high-quality neural machine translation and independent human references. The data was collected as part of the EU APE-QUEST project and comprises crawled content from EU websites with translation from English into three European languages: Dutch, French and Portuguese. Altogether, the data consists of around 31K tuples including a source sentence, the respective machine translation by a neural machine translation system, a post-edited version of such translation by a professional translator, and - where available - the original reference translation crawled from parallel language websites. We describe the data collection process, provide an analysis of the resulting post-edits and benchmark the data using state-of-the-art quality estimation and automatic post-editing models. One interesting by-product of our post-editing analysis suggests that neural systems built with publicly available general domain data can provide high-quality translations, even though comparison to human references suggests that this quality is quite low. This makes our dataset a suitable candidate to test evaluation metrics. The data is freely available as an ELRC-SHARE resource.
Reliably evaluating Machine Translation (MT) through automated metrics is a long-standing problem. One of the main challenges is the fact that multiple outputs can be equally valid. Attempts to minimise this issue include metrics that relax the matching of MT output and reference strings, and the use of multiple references. The latter has been shown to significantly improve the performance of evaluation metrics. However, collecting multiple references is expensive and in practice a single reference is generally used. In this paper, we propose an alternative approach: instead of modelling linguistic variation in human reference we exploit the MT model uncertainty to generate multiple diverse translations and use these: (i) as surrogates to reference translations; (ii) to obtain a quantification of translation variability to either complement existing metric scores or (iii) replace references altogether. We show that for a number of popular evaluation metrics our variability estimates lead to substantial improvements in correlation with human judgements of quality by up 15%.
We propose approaches to Quality Estimation (QE) for Machine Translation that explore both text and visual modalities for Multimodal QE. We compare various multimodality integration and fusion strategies. For both sentence-level and document-level predictions, we show that state-of-the-art neural and feature-based QE frameworks obtain better results when using the additional modality.
In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components, and/or delete information deemed unnecessary. Despite these varied range of possible text alterations, current models for automatic sentence simplification are evaluated using datasets that are focused on a single transformation, such as lexical paraphrasing or splitting. This makes it impossible to understand the ability of simplification models in more realistic settings. To alleviate this limitation, this paper introduces ASSET, a new dataset for assessing sentence simplification in English. ASSET is a crowdsourced multi-reference corpus where each simplification was produced by executing several rewriting transformations. Through quantitative and qualitative experiments, we show that simplifications in ASSET are better at capturing characteristics of simplicity when compared to other standard evaluation datasets for the task. Furthermore, we motivate the need for developing better methods for automatic evaluation using ASSET, since we show that current popular metrics may not be suitable when multiple simplification transformations are performed.
Recent advances in pre-trained multilingual language models lead to state-of-the-art results on the task of quality estimation (QE) for machine translation. A carefully engineered ensemble of such models won the QE shared task at WMT19. Our in-depth analysis, however, shows that the success of using pre-trained language models for QE is over-estimated due to three issues we observed in current QE datasets: (i) The distributions of quality scores are imbalanced and skewed towards good quality scores; (iii) QE models can perform well on these datasets while looking at only source or translated sentences; (iii) They contain statistical artifacts that correlate well with human-annotated QE labels. Our findings suggest that although QE models might capture fluency of translated sentences and complexity of source sentences, they cannot model adequacy of translations effectively.
Previous work on multimodal machine translation has shown that visual information is only needed in very specific cases, for example in the presence of ambiguous words where the textual context is not sufficient. As a consequence, models tend to learn to ignore this information. We propose a translate-and-refine approach to this problem where images are only used by a second stage decoder. This approach is trained jointly to generate a good first draft translation and to improve over this draft by (i) making better use of the target language textual context (both left and right-side contexts) and (ii) making use of visual context. This approach leads to the state of the art results. Additionally, we show that it has the ability to recover from erroneous or missing words in the source language.
We address the task of evaluating image description generation systems. We propose a novel image-aware metric for this task: VIFIDEL. It estimates the faithfulness of a generated caption with respect to the content of the actual image, based on the semantic similarity between labels of objects depicted in images and words in the description. The metric is also able to take into account the relative importance of objects mentioned in human reference descriptions during evaluation. Even if these human reference descriptions are not available, VIFIDEL can still reliably evaluate system descriptions. The metric achieves high correlation with human judgments on two well-known datasets and is competitive with metrics that depend on and rely exclusively on human references.
Recent work on visually grounded language learning has focused on broader applications of grounded representations, such as visual question answering and multimodal machine translation. In this paper we consider grounded word sense translation, i.e. the task of correctly translating an ambiguous source word given the corresponding textual and visual context. Our main objective is to investigate the extent to which images help improve word-level (lexical) translation quality. We do so by first studying the dataset for this task to understand the scope and challenges of the task. We then explore different data settings, image features, and ways of grounding to investigate the gain from using images in each of the combinations. We find that grounding on the image is specially beneficial in weaker unidirectional recurrent translation models. We observe that adding structured image information leads to stronger gains in lexical translation accuracy.
Current approaches to Text Simplification focus on simplifying sentences individually. However, certain simplification transformations span beyond single sentences (e.g. joining and re-ordering sentences). In this paper, we motivate the need for modelling the simplification task at the document level, and assess the performance of sequence-to-sequence neural models in this setup. We analyse parallel original-simplified documents created by professional editors and show that there are frequent rewriting transformations that are not restricted to sentence boundaries. We also propose strategies to automatically evaluate the performance of a simplification model on these cross-sentence transformations. Our experiments show the inability of standard sequence-to-sequence neural models to learn these transformations, and suggest directions towards document-level simplification.
A major obstacle to the development of Natural Language Processing (NLP) methods in the biomedical domain is data accessibility. This problem can be addressed by generating medical data artificially. Most previous studies have focused on the generation of short clinical text, and evaluation of the data utility has been limited. We propose a generic methodology to guide the generation of clinical text with key phrases. We use the artificial data as additional training data in two key biomedical NLP tasks: text classification and temporal relation extraction. We show that artificially generated training data used in conjunction with real training data can lead to performance boosts for data-greedy neural network algorithms. We also demonstrate the usefulness of the generated data for NLP setups where it fully replaces real training data.
This paper describes our submission to the WMT 2019 Chinese-English (zh-en) news translation shared task. Our systems are based on RNN architectures with pre-trained embeddings which utilize character and sub-character information. We compare models with these different granularity levels using different evaluating metics. We find that a finer granularity embeddings can help the model according to character level evaluation and that the pre-trained embeddings can also be beneficial for model performance marginally when the training data is limited.
We propose WMDO, a metric based on distance between distributions in the semantic vector space. Matching in the semantic space has been investigated for translation evaluation, but the constraints of a translation’s word order have not been fully explored. Building on the Word Mover’s Distance metric and various word embeddings, we introduce a fragmentation penalty to account for fluency of a translation. This word order extension is shown to perform better than standard WMD, with promising results against other types of metrics.
The IWSLT 2019 evaluation campaign featured three tasks: speech translation of (i) TED talks and (ii) How2 instructional videos from English into German and Portuguese, and (iii) text translation of TED talks from English into Czech. For the first two tasks we encouraged submissions of end- to-end speech-to-text systems, and for the second task participants could also use the video as additional input. We received submissions by 12 research teams. This overview provides detailed descriptions of the data and evaluation conditions of each task and reports results of the participating systems.
This paper describes the cascaded multimodal speech translation systems developed by Imperial College London for the IWSLT 2019 evaluation campaign. The architecture consists of an automatic speech recognition (ASR) system followed by a Transformer-based multimodal machine translation (MMT) system. While the ASR component is identical across the experiments, the MMT model varies in terms of the way of integrating the visual context (simple conditioning vs. attention), the type of visual features exploited (pooled, convolutional, action categories) and the underlying architecture. For the latter, we explore both the canonical transformer and its deliberation version with additive and cascade variants which differ in how they integrate the textual attention. Upon conducting extensive experiments, we found that (i) the explored visual integration schemes often harm the translation performance for the transformer and additive deliberation, but considerably improve the cascade deliberation; (ii) the transformer and cascade deliberation integrate the visual modality better than the additive deliberation, as shown by the incongruence analysis.
Devising metrics to assess translation quality has always been at the core of machine translation (MT) research. Traditional automatic reference-based metrics, such as BLEU, have shown correlations with human judgements of adequacy and fluency and have been paramount for the advancement of MT system development. Crowd-sourcing has popularised and enabled the scalability of metrics based on human judgments, such as subjective direct assessments (DA) of adequacy, that are believed to be more reliable than reference-based automatic metrics. Finally, task-based measurements, such as post-editing time, are expected to provide a more de- tailed evaluation of the usefulness of translations for a specific task. Therefore, while DA averages adequacy judgements to obtain an appraisal of (perceived) quality independently of the task, and reference-based automatic metrics try to objectively estimate quality also in a task-independent way, task-based metrics are measurements obtained either during or after performing a specific task. In this paper we argue that, although expensive, task-based measurements are the most reliable when estimating MT quality in a specific task; in our case, this task is post-editing. To that end, we report experiments on a dataset with newly-collected post-editing indicators and show their usefulness when estimating post-editing effort. Our results show that task-based metrics comparing machine-translated and post-edited versions are the best at tracking post-editing effort, as expected. These metrics are followed by DA, and then by metrics comparing the machine-translated version and independent references. We suggest that MT practitioners should be aware of these differences and acknowledge their implications when decid- ing how to evaluate MT for post-editing purposes.
Current work on multimodal machine translation (MMT) has suggested that the visual modality is either unnecessary or only marginally beneficial. We posit that this is a consequence of the very simple, short and repetitive sentences used in the only available dataset for the task (Multi30K), rendering the source text sufficient as context. In the general case, however, we believe that it is possible to combine visual and textual information in order to ground translations. In this paper we probe the contribution of the visual modality to state-of-the-art MMT models by conducting a systematic analysis where we partially deprive the models from source-side textual context. Our results show that under limited textual context, models are capable of leveraging the visual input to generate better translations. This contradicts the current belief that MMT models disregard the visual modality because of either the quality of the image features or the way they are integrated into the model.
Most text-to-text generation tasks, for example text summarisation and text simplification, require copying words from the input to the output. We introduce Copycat, a transformer-based pointer network for such tasks which obtains competitive results in abstractive text summarisation and generates more abstractive summaries. We propose a further extension of this architecture for automatic post-editing, where generation is conditioned over two inputs (source language and machine translation), and the model is capable of deciding where to copy information from. This approach achieves competitive performance when compared to state-of-the-art automated post-editing systems. More importantly, we show that it addresses a well-known limitation of automatic post-editing - overcorrecting translations - and that our novel mechanism for copying source language words improves the results.
We introduce EASSE, a Python package aiming to facilitate and standardise automatic evaluation and comparison of Sentence Simplification (SS) systems. EASSE provides a single access point to a broad range of evaluation resources: standard automatic metrics for assessing SS outputs (e.g. SARI), word-level accuracy scores for certain simplification transformations, reference-independent quality estimation features (e.g. compression ratio), and standard test data for SS evaluation (e.g. TurkCorpus). Finally, EASSE generates easy-to-visualise reports on the various metrics and features above and on how a particular SS output fares against reference simplifications. Through experiments, we show that these functionalities allow for better comparison and understanding of the performance of SS systems.
Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of “domain” adaption to noise. The recently created Machine Translation on Noisy Text task corpus provides noisy-clean parallel data for a few language pairs, but this data is very limited in size and diversity. The state-of-the-art approaches are heavily dependent on large volumes of back-translated data. This paper has two main contributions: Firstly, we propose new data augmentation methods to extend limited noisy data and further improve NMT robustness to noise while keeping the models small. Secondly, we explore the effect of utilizing noise from external data in the form of speech transcripts and show that it could help robustness.
Automatic Machine Translation (MT) evaluation is an active field of research, with a handful of new metrics devised every year. Evaluation metrics are generally benchmarked against manual assessment of translation quality, with performance measured in terms of overall correlation with human scores. Much work has been dedicated to the improvement of evaluation metrics to achieve a higher correlation with human judgments. However, little insight has been provided regarding the weaknesses and strengths of existing approaches and their behavior in different settings. In this work we conduct a broad meta-evaluation study of the performance of a wide range of evaluation metrics focusing on three major aspects. First, we analyze the performance of the metrics when faced with different levels of translation quality, proposing a local dependency measure as an alternative to the standard, global correlation coefficient. We show that metric performance varies significantly across different levels of MT quality: Metrics perform poorly when faced with low-quality translations and are not able to capture nuanced quality distinctions. Interestingly, we show that evaluating low-quality translations is also more challenging for humans. Second, we show that metrics are more reliable when evaluating neural MT than the traditional statistical MT systems. Finally, we show that the difference in the evaluation accuracy for different metrics is maintained even if the gold standard scores are based on different criteria.
Text simplification (TS) is a monolingual text-to-text transformation task where an original (complex) text is transformed into a target (simpler) text. Most recent work is based on sequence-to-sequence neural models similar to those used for machine translation (MT). Different from MT, TS data comprises more elaborate transformations, such as sentence splitting. It can also contain multiple simplifications of the same original text targeting different audiences, such as school grade levels. We explore these two features of TS to build models tailored for specific grade levels. Our approach uses a standard sequence-to-sequence architecture where the original sequence is annotated with information about the target audience and/or the (predicted) type of simplification operation. We show that it outperforms state-of-the-art TS approaches (up to 3 and 12 BLEU and SARI points, respectively), including when training data for the specific complex-simple combination of grade levels is not available, i.e. zero-shot learning.
Predicting Machine Translation (MT) quality can help in many practical tasks such as MT post-editing. The performance of Quality Estimation (QE) methods has drastically improved recently with the introduction of neural approaches to the problem. However, thus far neural approaches have only been designed for word and sentence-level prediction. We present a neural framework that is able to accommodate neural QE approaches at these fine-grained levels and generalize them to the level of documents. We test the framework with two sentence-level neural QE approaches: a state of the art approach that requires extensive pre-training, and a new light-weight approach that we propose, which employs basic encoders. Our approach is significantly faster and yields performance improvements for a range of document-level quality estimation tasks. To our knowledge, this is the first neural architecture for document-level QE. In addition, for the first time we apply QE models to the output of both statistical and neural MT systems for a series of European languages and highlight the new challenges resulting from the use of neural MT.
The use of explicit object detectors as an intermediate step to image captioning – which used to constitute an essential stage in early work – is often bypassed in the currently dominant end-to-end approaches, where the language model is conditioned directly on a mid-level image embedding. We argue that explicit detections provide rich semantic information, and can thus be used as an interpretable representation to better understand why end-to-end image captioning systems work well. We provide an in-depth analysis of end-to-end image captioning by exploring a variety of cues that can be derived from such object detections. Our study reveals that end-to-end image captioning systems rely on matching image representations to generate captions, and that encoding the frequency, size and position of objects are complementary and all play a role in forming a good image representation. It also reveals that different object categories contribute in different ways towards image captioning.
We address the task of detecting foiled image captions, i.e. identifying whether a caption contains a word that has been deliberately replaced by a semantically similar word, thus rendering it inaccurate with respect to the image being described. Solving this problem should in principle require a fine-grained understanding of images to detect subtle perturbations in captions. In such contexts, encoding sufficiently descriptive image information becomes a key challenge. In this paper, we demonstrate that it is possible to solve this task using simple, interpretable yet powerful representations based on explicit object information over multilayer perceptron models. Our models achieve state-of-the-art performance on a recently published dataset, with scores exceeding those achieved by humans on the task. We also measure the upper-bound performance of our models using gold standard annotations. Our study and analysis reveals that the simpler model performs well even without image information, suggesting that the dataset contains strong linguistic bias.
Machine Translation systems are usually evaluated and compared using automated evaluation metrics such as BLEU and METEOR to score the generated translations against human translations. However, the interaction with the output from the metrics is relatively limited and results are commonly a single score along with a few additional statistics. Whilst this may be enough for system comparison it does not provide much useful feedback or a means for inspecting translations and their respective scores. VisEval Metric Viewer VEMV is a tool designed to provide visualisation of multiple evaluation scores so they can be easily interpreted by a user. VEMV takes in the source, reference, and hypothesis files as parameters, and scores the hypotheses using several popular evaluation metrics simultaneously. Scores are produced at both the sentence and dataset level and results are written locally to a series of HTML files that can be viewed on a web browser. The individual scored sentences can easily be inspected using powerful search and selection functions and results can be visualised with graphical representations of the scores and distributions.
We report the findings of the second Complex Word Identification (CWI) shared task organized as part of the BEA workshop co-located with NAACL-HLT’2018. The second CWI shared task featured multilingual and multi-genre datasets divided into four tracks: English monolingual, German monolingual, Spanish monolingual, and a multilingual track with a French test set, and two tasks: binary classification and probabilistic classification. A total of 12 teams submitted their results in different task/track combinations and 11 of them wrote system description papers that are referred to in this report and appear in the BEA workshop proceedings.
We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn ‘distributional similarity’ in a multimodal feature space, by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the ‘image’ side of image captioning, and vary the input image representation but keep the RNN text generation model of a CNN-RNN constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; (ii) experience virtually no significant performance loss when a high dimensional representation is compressed to a lower dimensional space; (iii) cluster images with similar visual and linguistic information together. Our experiments all point to one fact: that our distributional similarity hypothesis holds. We conclude that, regardless of the image representation, image captioning systems seem to match images and generate captions in a learned joint image-text semantic subspace.
A popular application of machine translation (MT) is gisting: MT is consumed as is to make sense of text in a foreign language. Evaluation of the usefulness of MT for gisting is surprisingly uncommon. The classical method uses reading comprehension questionnaires (RCQ), in which informants are asked to answer professionally-written questions in their language about a foreign text that has been machine-translated into their language. Recently, gap-filling (GF), a form of cloze testing, has been proposed as a cheaper alternative to RCQ. In GF, certain words are removed from reference translations and readers are asked to fill the gaps left using the machine-translated text as a hint. This paper reports, for the first time, a comparative evaluation, using both RCQ and GF, of translations from multiple MT systems for the same foreign texts, and a systematic study on the effect of variables such as gap density, gap-selection strategies, and document context in GF. The main findings of the study are: (a) both RCQ and GF clearly identify MT to be useful; (b) global RCQ and GF rankings for the MT systems are mostly in agreement; (c) GF scores vary very widely across informants, making comparisons among MT systems hard, and (d) unlike RCQ, which is framed around documents, GF evaluation can be framed at the sentence level. These findings support the use of GF as a cheaper alternative to RCQ.
We present the results from the third shared task on multimodal machine translation. In this task a source sentence in English is supplemented by an image and participating systems are required to generate a translation for such a sentence into German, French or Czech. The image can be used in addition to (or instead of) the source sentence. This year the task was extended with a third target language (Czech) and a new test set. In addition, a variant of this task was introduced with its own test set where the source sentence is given in multiple languages: English, French and German, and participating systems are required to generate a translation in Czech. Seven teams submitted 45 different systems to the two variants of the task. Compared to last year, the performance of the multimodal submissions improved, but text-only systems remain competitive.
This paper describes the University of Sheffield’s submissions to the WMT18 Multimodal Machine Translation shared task. We participated in both tasks 1 and 1b. For task 1, we build on a standard sequence to sequence attention-based neural machine translation system (NMT) and investigate the utility of multimodal re-ranking approaches. More specifically, n-best translation candidates from this system are re-ranked using novel multimodal cross-lingual word sense disambiguation models. For task 1b, we explore three approaches: (i) re-ranking based on cross-lingual word sense disambiguation (as for task 1), (ii) re-ranking based on consensus of NMT n-best lists from German-Czech, French-Czech and English-Czech systems, and (iii) data augmentation by generating English source data through machine translation from French to English and from German to English followed by hypothesis selection using a multimodal-reranker.
We report the results of the WMT18 shared task on Quality Estimation, i.e. the task of predicting the quality of the output of machine translation systems at various granularity levels: word, phrase, sentence and document. This year we include four language pairs, three text domains, and translations produced by both statistical and neural machine translation systems. Participating teams from ten institutions submitted a variety of systems to different task variants and language pairs.
In this paper we present the University of Sheffield submissions for the WMT18 Quality Estimation shared task. We discuss our submissions to all four sub-tasks, where ours is the only team to participate in all language pairs and variations (37 combinations). Our systems show competitive results and outperform the baseline in nearly all cases.
Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification operations, such as deletions or substitutions, on existing data. While the recently introduced Newsela corpus has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from explicit annotations. These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult. End-to-end models also make it hard to interpret what is actually learned from data. We propose a method that decomposes the task of TS into its sub-problems. We devise a way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations. Finally, we provide insights on the types of transformations that different approaches can model.
We introduce MASSAlign: a Python library for the alignment and annotation of monolingual comparable documents. MASSAlign offers easy-to-use access to state of the art algorithms for paragraph and sentence-level alignment, as well as novel algorithms for word-level annotation of transformation operations between aligned sentences. In addition, MASSAlign provides a visualization module to display and analyze the alignments and annotations performed.
We describe MUSST, a multilingual syntactic simplification tool. The tool supports sentence simplifications for English, Italian and Spanish, and can be easily extended to other languages. Our implementation includes a set of general-purpose simplification rules, as well as a sentence selection module (to select sentences to be simplified) and a confidence model (to select only promising simplifications). The tool was implemented in the context of the European project SIMPATICO on text simplification for Public Administration (PA) texts. Our evaluation on sentences in the PA domain shows that we obtain correct simplifications for 76% of the simplified cases in English, 71% of the cases in Spanish. For Italian, the results are lower (38%) but the tool is still under development.
There is no question that our research community have, and still has been producing an insurmountable amount of interesting strategies, models and tools to a wide array of problems and challenges in diverse areas of knowledge. But for as long as interesting work has existed, we’ve been plagued by a great unsolved mystery: how come there is so much interesting work being published in conferences, but not as many interesting and engaging posters and presentations being featured in them? In this tutorial, we present practical step-by-step makeup solutions for poster, slides and oral presentations in order to help researchers who feel like they are not able to convey the importance of their research to the community in conferences.
Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring MT quality estimation (MTQE) data. The task obtained strong participation from 31 teams, with 17 participating in all language tracks. We summarize performance and review a selection of well performing methods. Analysis highlights common errors, providing insight into the limitations of existing models. To support ongoing work on semantic representations, the STS Benchmark is introduced as a new shared training and evaluation set carefully selected from the corpus of English STS shared task data (2012-2017).
This paper revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational methods can discriminate between complex and non-complex words. Furthermore, we analyze the classification performance to understand what makes lexical complexity challenging. Our findings show that most systems performed poorly on the SemEval CWI dataset, and one of the reasons for that is the way in which human annotation was performed.
The language that we produce reflects our personality, and various personal and demographic characteristics can be detected in natural language texts. We focus on one particular personal trait of the author, gender, and study how it is manifested in original texts and in translations. We show that author’s gender has a powerful, clear signal in originals texts, but this signal is obfuscated in human and machine translation. We then propose simple domain-adaptation techniques that help retain the original gender traits in the translation, without harming the quality of the translation, thereby creating more personalized machine translation systems.
We present a new Lexical Simplification approach that exploits Neural Networks to learn substitutions from the Newsela corpus - a large set of professionally produced simplifications. We extract candidate substitutions by combining the Newsela corpus with a retrofitted context-aware word embeddings model and rank them using a new neural regression model that learns rankings from annotated data. This strategy leads to the highest Accuracy, Precision and F1 scores to date in standard datasets for the task.
We report three user studies in which the Lexical Simplification needs of non-native English speakers are investigated. Our analyses feature valuable new insight on the relationship between the non-natives’ notion of complexity and various morphological, semantic and lexical word properties. Some of our findings contradict long-standing misconceptions about word simplicity. The data produced in our studies consists of 211,564 annotations made by 1,100 volunteers, which we hope will guide forthcoming research on Text Simplification for non-native speakers of English.
Exploring language usage through frequency analysis in large corpora is a defining feature in most recent work in corpus and computational linguistics. From a psycholinguistic perspective, however, the corpora used in these contributions are often not representative of language usage: they are either domain-specific, limited in size, or extracted from unreliable sources. In an effort to address this limitation, we introduce SubIMDB, a corpus of everyday language spoken text we created which contains over 225 million words. The corpus was extracted from 38,102 subtitles of family, comedy and children movies and series, and is the first sizeable structured corpus of subtitles made available. Our experiments show that word frequency norms extracted from this corpus are more effective than those from well-known norms such as Kucera-Francis, HAL and SUBTLEXus in predicting various psycholinguistic properties of words, such as lexical decision times, familiarity, age of acquisition and simplicity. We also provide evidence that contradict the long-standing assumption that the ideal size for a corpus can be determined solely based on how well its word frequencies correlate with lexical decision times.
We introduce Anita: a flexible and intelligent Text Adaptation tool for web content that provides Text Simplification and Text Enhancement modules. Anita’s simplification module features a state-of-the-art system that adapts texts according to the needs of individual users, and its enhancement module allows the user to search for a word’s definitions, synonyms, translations, and visual cues through related images. These utilities are brought together in an easy-to-use interface of a freely available web browser extension.
Quality Estimation (QE) of language output applications is a research area that has been attracting significant attention. The goal of QE is to estimate the quality of language output applications without the need of human references. Instead, machine learning algorithms are used to build supervised models based on a few labelled training instances. Such models are able to generalise over unseen data and thus QE is a robust method applicable to scenarios where human input is not available or possible. One such a scenario where QE is particularly appealing is that of Machine Translation, where a score for predicted quality can help decide whether or not a translation is useful (e.g. for post-editing) or reliable (e.g. for gisting). Other potential applications within Natural Language Processing (NLP) include Text Summarisation and Text Simplification. In this tutorial we present the task of QE and its application in NLP, focusing on Machine Translation. We also introduce QuEst++, a toolkit for QE that encompasses feature extraction and machine learning, and propose a practical activity to extend this toolkit in various ways.
This paper presents our work towards a novel approach for Quality Estimation (QE) of machine translation based on sequences of adjacent words, the so-called phrases. This new level of QE aims to provide a natural balance between QE at word and sentence-level, which are either too fine grained or too coarse levels for some applications. However, phrase-level QE implies an intrinsic challenge: how to segment a machine translation into sequence of words (contiguous or not) that represent an error. We discuss three possible segmentation strategies to automatically extract erroneous phrases. We evaluate these strategies against annotations at phrase-level produced by humans, using a new dataset collected for this purpose.
Lexical Simplification is the task of replacing complex words in a text with simpler alternatives. A variety of strategies have been devised for this challenge, yet there has been little effort in comparing their performance. In this contribution, we present a benchmarking of several Lexical Simplification systems. By combining resources created in previous work with automatic spelling and inflection correction techniques, we introduce BenchLS: a new evaluation dataset for the task. Using BenchLS, we evaluate the performance of solutions for various steps in the typical Lexical Simplification pipeline, both individually and jointly. This is the first time Lexical Simplification systems are compared in such fashion on the same data, and the findings introduce many contributions to the field, revealing several interesting properties of the systems evaluated.
Effectively assessing Natural Language Processing output tasks is a challenge for research in the area. In the case of Machine Translation (MT), automatic metrics are usually preferred over human evaluation, given time and budget constraints.However, traditional automatic metrics (such as BLEU) are not reliable for absolute quality assessment of documents, often producing similar scores for documents translated by the same MT system.For scenarios where absolute labels are necessary for building models, such as document-level Quality Estimation, these metrics can not be fully trusted. In this paper, we introduce a corpus of reading comprehension tests based on machine translated documents, where we evaluate documents based on answers to questions by fluent speakers of the target language. We describe the process of creating such a resource, the experiment design and agreement between the test takers. Finally, we discuss ways to convert the reading comprehension test into document-level quality scores.
We present Marmot~― a new toolkit for quality estimation (QE) of machine translation output. Marmot contains utilities targeted at quality estimation at the word and phrase level. However, due to its flexibility and modularity, it can also be extended to work at the sentence level. In addition, it can be used as a framework for extracting features and learning models for many common natural language processing tasks. The tool has a set of state-of-the-art features for QE, and new features can easily be added. The tool is open-source and can be downloaded from https://github.com/qe-team/marmot/
We describe COHERE, our coherence toolkit which incorporates various complementary models for capturing and measuring different aspects of text coherence. In addition to the traditional entity grid model (Lapata, 2005) and graph-based metric (Guinaudeau and Strube, 2013), we provide an implementation of a state-of-the-art syntax-based model (Louis and Nenkova, 2012), as well as an adaptation of this model which shows significant performance improvements in our experiments. We benchmark these models using the standard setting for text coherence: original documents and versions of the document with sentences in shuffled order.
Structural kernels are a flexible learning paradigm that has been widely used in Natural Language Processing. However, the problem of model selection in kernel-based methods is usually overlooked. Previous approaches mostly rely on setting default values for kernel hyperparameters or using grid search, which is slow and coarse-grained. In contrast, Bayesian methods allow efficient model selection by maximizing the evidence on the training data through gradient-based methods. In this paper we show how to perform this in the context of structural kernels by using Gaussian Processes. Experimental results on tree kernels show that this procedure results in better prediction performance compared to hyperparameter optimization via grid search. The framework proposed in this paper can be adapted to other structures besides trees, e.g., strings and graphs, thereby extending the utility of kernel-based methods.
We present a first attempt at predicting the quality of translations produced by human, professional translators. We examine datasets annotated for quality at sentence- and word-level for four language pairs and provide experiments with prediction models for these datasets. We compare the performance of such models against that of models built from machine translations, highlighting a number of challenges in estimating quality and detecting errors in human translations.
We present QUEST, an open source framework for translation quality estimation. QUEST provides a wide range of feature extractors from source and translation texts and external resources and tools. These go from simple, language-independent features, to advanced, linguistically motivated features. They include features that rely on information from the translation system and features that are oblivious to the way translations were produced. In addition, it provides wrappers for a well-known machine learning toolkit, scikit-learn, including techniques for feature selection and model building, as well as parameter optimisation. We also present a Web interface and functionalities for non-expert users. Using this interface, quality predictions (or internal features of the framework) can be obtained without the installation of the toolkit and the building of prediction models. The interface also provides a ranking method for multiple translations given for the same source text according to their predicted quality.
This paper presents a new active learning technique for machine translation based on quality estimation of automatically translated sentences. It uses an error-driven strategy, i.e., it assumes that the more errors an automatically translated sentence contains, the more informative it is for the translation system. Our approach is based on a quality estimation technique which involves a wider range of features of the source text, automatic translation, and machine translation system compared to previous work. In addition, we enhance the machine translation system training data with post-edited machine translations of the sentences selected, instead of simulating this using previously created reference translations. We found that re-training systems with additional post-edited data yields higher quality translations regardless of the selection strategy used. We relate this to the fact that post-editions tend to be closer to source sentences as compared to references, making the rule extraction process more reliable.
We present a new version of QUEST ― an open source framework for machine translation quality estimation ― which brings a number of improvements: (i) it provides a Web interface and functionalities such that non-expert users, e.g. translators or lay-users of machine translations, can get quality predictions (or internal features of the framework) for translations without having to install the toolkit, obtain resources or build prediction models; (ii) it significantly improves over the previous runtime performance by keeping resources (such as language models) in memory; (iii) it provides an option for users to submit the source text only and automatically obtain translations from Bing Translator; (iv) it provides a ranking of multiple translations submitted by users for each source text according to their estimated quality. We exemplify the use of this new version through some experiments with the framework.
The University of Sheffield (USFD) participated in the International Workshop for Spoken Language Translation (IWSLT) in 2014. In this paper, we will introduce the USFD SLT system for IWSLT. Automatic speech recognition (ASR) is achieved by two multi-pass deep neural network systems with adaptation and rescoring techniques. Machine translation (MT) is achieved by a phrase-based system. The USFD primary system incorporates state-of-the-art ASR and MT techniques and gives a BLEU score of 23.45 and 14.75 on the English-to-French and English-to-German speech-to-text translation task with the IWSLT 2014 data. The USFD contrastive systems explore the integration of ASR and MT by using a quality estimation system to rescore the ASR outputs, optimising towards better translation. This gives a further 0.54 and 0.26 BLEU improvement respectively on the IWSLT 2012 and 2014 evaluation data.
Post-editing machine translations has been attracting increasing attention both as a common practice within the translation industry and as a way to evaluate Machine Translation (MT) quality via edit distance metrics between the MT and its post-edited version. Commonly used metrics such as HTER are limited in that they cannot fully capture the effort required for post-editing. Particularly, the cognitive effort required may vary for different types of errors and may also depend on the context. We suggest post-editing time as a way to assess some of the cognitive effort involved in post-editing. This paper presents two experiments investigating the connection between post-editing time and cognitive effort. First, we examine whether sentences with long and short post-editing times involve edits of different levels of difficulty. Second, we study the variability in post-editing time and other statistics among editors.
Given the significant improvements in Machine Translation (MT) quality and the increasing demand for translations, post-editing of automatic translations is becoming a popular practice in the translation industry. It has been shown to allow for much larger volumes of translations to be produced, saving time and costs. In addition, the post-editing of automatic translations can help understand problems in such translations and this can be used as feedback for researchers and developers to improve MT systems. Finally, post-editing can be used as a way of evaluating the quality of translations in terms of how much post-editing effort these translations require. We describe a standalone tool that has two main purposes: facilitate the post-editing of translations from any MT system so that they reach publishable quality and collect sentence-level information from the post-editing process, e.g.: post-editing time and detailed keystroke statistics.
We describe a dataset containing 16,000 translations produced by four machine translation systems and manually annotated for quality by professional translators. This dataset can be used in a range of tasks assessing machine translation evaluation metrics, from basic correlation analysis to training and test of machine learning-based metrics. By providing a standard dataset for such tasks, we hope to encourage the development of better MT evaluation metrics.
Although Machine Translation (MT) has been attracting more and more attention from the translation industry, the quality of current MT systems still requires humans to post-edit translations to ensure their quality. The time necessary to post-edit bad quality translations can be the same or even longer than that of translating without an MT system. It is well known, however, that the quality of an MT system is generally not homogeneous across all translated segments. In order to make MT more useful to the translation industry, it is therefore crucial to have a mechanism to judge MT quality at the segment level to prevent bad quality translations from being post-edited within the translation workflow. We describe an approach to estimate translation post-editing effort at sentence level in terms of Human-targeted Translation Edit Rate (HTER) based on a number of features reflecting the difficulty of translating the source sentence and discrepancies between the source and translation sentences. HTER is a simple metric and obtaining HTER annotated data can be made part of the translation workflow. We show that this approach is more reliable at filtering out bad translations than other simple criteria commonly used in the translation industry, such as sentence length.
We describe an effort to improve standard reference-based metrics for Machine Translation (MT) evaluation by enriching them with Confidence Estimation (CE) features and using a learning mechanism trained on human annotations. Reference-based MT evaluation metrics compare the system output against reference translations looking for overlaps at different levels (lexical, syntactic, and semantic). These metrics aim at comparing MT systems or analyzing the progress of a given system and are known to have reasonably good correlation with human judgments at the corpus level, but not at the segment level. CE metrics, on the other hand, target the system in use, providing a quality score to the end-user for each translated segment. They cannot rely on reference translations, and use instead information extracted from the input text, system output and possibly external corpora to train machine learning algorithms. These metrics correlate better with human judgments at the segment level. However, they are usually highly biased by difficulty level of the input segment, and therefore are less appropriate for comparing multiple systems translating the same input segments. We show that these two classes of metrics are complementary and can be combined to provide MT evaluation metrics that achieve higher correlation with human judgments at the segment level.