Sequence to sequence learning models still require several days to reach state of the art performance on large benchmark datasets using a single machine. This paper shows that reduced precision and large batch training can speedup training by nearly 5x on a single 8-GPU machine with careful tuning and implementation. On WMT’14 English-German translation, we match the accuracy of Vaswani et al. (2017) in under 5 hours when training on 8 GPUs and we obtain a new state of the art of 29.3 BLEU after training for 85 minutes on 128 GPUs. We further improve these results to 29.8 BLEU by training on the much larger Paracrawl dataset. On the WMT’14 English-French task, we obtain a state-of-the-art BLEU of 43.2 in 8.5 hours on 128 GPUs.

Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs. They mainly do well for Indo-European language pairs, where the languages share the same writing system. However, for translating between Chinese and English, the gap between the two different writing systems poses a major challenge because of a lack of systematic correspondence between the individual linguistic units. In this paper, we enable character-level NMT for Chinese, by breaking down Chinese characters into linguistic units similar to that of Indo-European languages. We use the Wubi encoding scheme, which preserves the original shape and semantic information of the characters, while also being reversible. We show promising results from training Wubi-based models on the character- and subword-level with recurrent as well as convolutional models.

Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.

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.

We present an analysis of a number of coreference phenomena in English-Croatian human and machine translations. The aim is to shed light on the differences in the way these structurally different languages make use of discourse information and provide insights for discourse-aware machine translation system development. The phenomena are automatically identified in parallel data using annotation produced by parsers and word alignment tools, enabling us to pinpoint patterns of interest in both languages. We make the analysis more fine-grained by including three corpora pertaining to three different registers. In a second step, we create a test set with the challenging linguistic constructions and use it to evaluate the performance of three MT systems. We show that both SMT and NMT systems struggle with handling these discourse phenomena, even though NMT tends to perform somewhat better than SMT. By providing an overview of patterns frequently occurring in actual language use, as well as by pointing out the weaknesses of current MT systems that commonly mistranslate them, we hope to contribute to the effort of resolving the issue of discourse phenomena in MT applications.

Cross-sentence context can provide valuable information in Machine Translation and is critical for translation of anaphoric pronouns and for providing consistent translations. In this paper, we devise simple oracle experiments targeting coreference and coherence. Oracles are an easy way to evaluate the effect of different discourse-level phenomena in NMT using BLEU and eliminate the necessity to manually define challenge sets for this purpose. We propose two context-aware NMT models and compare them against models working on a concatenation of consecutive sentences. Concatenation models perform better, but are computationally expensive. We show that NMT models taking advantage of context oracle signals can achieve considerable gains in BLEU, of up to 7.02 BLEU for coreference and 1.89 BLEU for coherence on subtitles translation. Access to strong signals allows us to make clear comparisons between context-aware models.

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.

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we investigate other forms of sharing in between no sharing and hard equality of parameters. In particular, we propose a structure-aware output layer which captures the semantic structure of the output space of words within a joint input-output embedding. The model is a generalized form of weight tying which shares parameters but allows learning a more flexible relationship with input word embeddings and allows the effective capacity of the output layer to be controlled. In addition, the model shares weights across output classifiers and translation contexts which allows it to better leverage prior knowledge about them. Our evaluation on English-to-Finnish and English-to-German datasets shows the effectiveness of the method against strong encoder-decoder baselines trained with or without weight tying.

We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a language-independent representation by performing direct zero-shot translation (without using pivot translation), and by using the source sentence embeddings to create an English Yelp review classifier that, through the mediation of the neural interlingua, can also classify French and German reviews. Furthermore, we show that, despite using a smaller number of parameters than a pairwise collection of bilingual NMT models, our approach produces comparable BLEU scores for each language pair in WMT15.

Embedding and projection matrices are commonly used in neural language models (NLM) as well as in other sequence processing networks that operate on large vocabularies. We examine such matrices in fine-tuned language models and observe that a NLM learns word vectors whose norms are related to the word frequencies. We show that by initializing the weight norms with scaled log word counts, together with other techniques, lower perplexities can be obtained in early epochs of training. We also introduce a weight norm regularization loss term, whose hyperparameters are tuned via a grid search. With this method, we are able to significantly improve perplexities on two word-level language modeling tasks (without dynamic evaluation): from 54.44 to 53.16 on Penn Treebank (PTB) and from 61.45 to 60.13 on WikiText-2 (WT2).

Recent works in neural machine translation have begun to explore document translation. However, translating online multi-speaker conversations is still an open problem. In this work, we propose the task of translating Bilingual Multi-Speaker Conversations, and explore neural architectures which exploit both source and target-side conversation histories for this task. To initiate an evaluation for this task, we introduce datasets extracted from Europarl v7 and OpenSubtitles2016. Our experiments on four language-pairs confirm the significance of leveraging conversation history, both in terms of BLEU and manual evaluation.

We reassess a recent study (Hassan et al., 2018) that claimed that machine translation (MT) has reached human parity for the translation of news from Chinese into English, using pairwise ranking and considering three variables that were not taken into account in that previous study: the language in which the source side of the test set was originally written, the translation proficiency of the evaluators, and the provision of inter-sentential context. If we consider only original source text (i.e. not translated from another language, or translationese), then we find evidence showing that human parity has not been achieved. We compare the judgments of professional translators against those of non-experts and discover that those of the experts result in higher inter-annotator agreement and better discrimination between human and machine translations. In addition, we analyse the human translations of the test set and identify important translation issues. Finally, based on these findings, we provide a set of recommendations for future human evaluations of MT.

To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each component’s contribution to, and capacity for, domain adaptation. We find that freezing any single component during continued training has minimal impact on performance, and that performance is surprisingly good when a single component is adapted while holding the rest of the model fixed. We also find that continued training does not move the model very far from the out-of-domain model, compared to a sensitivity analysis metric, suggesting that the out-of-domain model can provide a good generic initialization for the new domain.

Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet. Denoising is concerned with a different type of data quality and tries to reduce the negative impact of data noise on MT training, in particular, neural MT (NMT) training. This paper generalizes methods for measuring and selecting data for domain MT and applies them to denoising NMT training. The proposed approach uses trusted data and a denoising curriculum realized by online data selection. Intrinsic and extrinsic evaluations of the approach show its significant effectiveness for NMT to train on data with severe noise.

Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms. While Phrase-Based MT can seamlessly integrate very large language models trained on billions of sentences, the best option for Neural MT developers seems to be the generation of artificial parallel data through back-translation - a technique that fails to fully take advantage of existing datasets. In this paper, we conduct a systematic study of back-translation, comparing alternative uses of monolingual data, as well as multiple data generation procedures. Our findings confirm that back-translation is very effective and give new explanations as to why this is the case. We also introduce new data simulation techniques that are almost as effective, yet much cheaper to implement.

Both research and commercial machine translation have so far neglected the importance of properly handling the spelling, lexical and grammar divergences occurring among language varieties. Notable cases are standard national varieties such as Brazilian and European Portuguese, and Canadian and European French, which popular online machine translation services are not keeping distinct. We show that an evident side effect of modeling such varieties as unique classes is the generation of inconsistent translations. In this work, we investigate the problem of training neural machine translation from English to specific pairs of language varieties, assuming both labeled and unlabeled parallel texts, and low-resource conditions. We report experiments from English to two pairs of dialects, European-Brazilian Portuguese and European-Canadian French, and two pairs of standardized varieties, Croatian-Serbian and Indonesian-Malay. We show significant BLEU score improvements over baseline systems when translation into similar languages is learned as a multilingual task with shared representations.

This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclusively for bilingual sentence pairs that are translations of each other. This is achieved using a novel training method that introduces hard negatives consisting of sentences that are not translations but have some degree of semantic similarity. The quality of the resulting embeddings are evaluated on parallel corpus reconstruction and by assessing machine translation systems trained on gold vs. mined sentence pairs. We find that the sentence embeddings can be used to reconstruct the United Nations Parallel Corpus (Ziemski et al., 2016) at the sentence-level with a precision of 48.9% for en-fr and 54.9% for en-es. When adapted to document-level matching, we achieve a parallel document matching accuracy that is comparable to the significantly more computationally intensive approach of Uszkoreit et al. (2010). Using reconstructed parallel data, we are able to train NMT models that perform nearly as well as models trained on the original data (within 1-2 BLEU).

This work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture. We demonstrate that alignment extraction in transformer models can be improved by augmenting an additional alignment head to the multi-head source-to-target attention component. This is used to compute sharper attention weights. We describe how to use the alignment head to achieve competitive performance. To study the effect of adding the alignment head, we simulate a dictionary-guided translation task, where the user wants to guide translation using pre-defined dictionary entries. Using the proposed approach, we achieve up to 3.8% BLEU improvement when using the dictionary, in comparison to 2.4% BLEU in the baseline case. We also propose alignment pruning to speed up decoding in alignment-based neural machine translation (ANMT), which speeds up translation by a factor of 1.8 without loss in translation performance. We carry out experiments on the shared WMT 2016 English→Romanian news task and the BOLT Chinese→English discussion forum task.

The field of machine translation faces an under-recognized problem because of inconsistency in the reporting of scores from its dominant metric. Although people refer to “the” BLEU score, BLEU is in fact a parameterized metric whose values can vary wildly with changes to these parameters. These parameters are often not reported or are hard to find, and consequently, BLEU scores between papers cannot be directly compared. I quantify this variation, finding differences as high as 1.8 between commonly used configurations. The main culprit is different tokenization and normalization schemes applied to the reference. Pointing to the success of the parsing community, I suggest machine translation researchers settle upon the BLEU scheme used by the annual Conference on Machine Translation (WMT), which does not allow for user-supplied reference processing, and provide a new tool, SACREBLEU, to facilitate this.

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.

Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for NMT training: We combine the scores of a pre-trained and fixed language model (LM) with the scores of a translation model (TM) while the TM is trained from scratch. To achieve that, we train the translation model to predict the residual probability of the training data added to the prediction of the LM. This enables the TM to focus its capacity on modeling the source sentence since it can rely on the LM for fluency. We show that our method outperforms previous approaches to integrate LMs into NMT while the architecture is simpler as it does not require gating networks to balance TM and LM. We observe gains of between +0.24 and +2.36 BLEU on all four test sets (English-Turkish, Turkish-English, Estonian-English, Xhosa-English) on top of ensembles without LM. We compare our method with alternative ways to utilize monolingual data such as backtranslation, shallow fusion, and cold fusion.

We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.

Data selection is a process used in selecting a subset of parallel data for the training of machine translation (MT) systems, so that 1) resources for training might be reduced, 2) trained models could perform better than those trained with the whole corpus, and/or 3) trained models are more tailored to specific domains. It has been shown that for statistical MT (SMT), the use of data selection helps improve the MT performance significantly. In this study, we reviewed three data selection approaches for MT, namely Term Frequency– Inverse Document Frequency, Cross-Entropy Difference and Feature Decay Algorithm, and conducted experiments on Neural Machine Translation (NMT) with the selected data using the three approaches. The results showed that for NMT systems, using data selection also improved the performance, though the gain is not as much as for SMT systems.

We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems. We build a translation system that addresses these challenges using eight European language families as our test ground. Firstly, we add the source and the target family labels and study intra-family and inter-family influences for effective cross-lingual transfer. We achieve an improvement of +9.9 in BLEU score for English-Swedish translation using eight families compared to the single-family multi-source multi-target baseline. Moreover, we find that training on two neighboring families closest to the low-resource language is often enough. Secondly, we construct an ablation study and find that reasonably good results can be achieved even with considerably less target data. Thirdly, we address the variable-binding problem by building an order-preserving named entity translation model. We obtain 60.6% accuracy in qualitative evaluation where our translations are akin to human translations in a preliminary study.

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We present a simple transfer learning method, where we first train a “parent” model for a high-resource language pair and then continue the training on a low-resource pair only by replacing the training corpus. This “child” model performs significantly better than the baseline trained for low-resource pair only. We are the first to show this for targeting different languages, and we observe the improvements even for unrelated languages with different alphabets.

In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the encoder-decoder attention in the Transformer architecture. We propose four different input combination strategies for the encoder-decoder attention: serial, parallel, flat, and hierarchical. We evaluate our methods on tasks of multimodal translation and translation with multiple source languages. The experiments show that the models are able to use multiple sources and improve over single source baselines.

In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained models. However, these improvements are not uniform; often multilingual parameter sharing results in a decrease in accuracy due to translation models not being able to accommodate different languages in their limited parameter space. In this work, we examine parameter sharing techniques that strike a happy medium between full sharing and individual training, specifically focusing on the self-attentional Transformer model. We find that the full parameter sharing approach leads to increases in BLEU scores mainly when the target languages are from a similar language family. However, even in the case where target languages are from different families where full parameter sharing leads to a noticeable drop in BLEU scores, our proposed methods for partial sharing of parameters can lead to substantial improvements in translation accuracy.