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.

This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2018. Participants were asked to build machine translation systems for any of 7 language pairs in both directions, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. This year, we also opened up the task to additional test sets to probe specific aspects of translation.

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.

Machine translation enables the automatic translation of textual documents between languages and can facilitate access to information only available in a given language for non-speakers of this language, e.g. research results presented in scientific publications. In this paper, we provide an overview of the Biomedical Translation shared task in the Workshop on Machine Translation (WMT) 2018, which specifically examined the performance of machine translation systems for biomedical texts. This year, we provided test sets of scientific publications from two sources (EDP and Medline) and for six language pairs (English with each of Chinese, French, German, Portuguese, Romanian and Spanish). We describe the development of the various test sets, the submissions that we received and the evaluations that we carried out. We obtained a total of 39 runs from six teams and some of this year’s BLEU scores were somewhat higher that last year’s, especially for teams that made use of biomedical resources or state-of-the-art MT algorithms (e.g. Transformer). Finally, our manual evaluation scored automatic translations higher than the reference translations for German and Spanish.

This paper describes the Global Tone Communication Co., Ltd.’s submission of the WMT18 shared news translation task. We participated in the English-to-Chinese direction and get the best BLEU (43.8) scores among all the participants. The submitted system focus on data clearing and techniques to build a competitive model for this task. Unlike other participants, the submitted system are mainly relied on the data filtering to obtain the best BLEU score. We do data filtering not only for provided sentences but also for the back translated sentences. The techniques we apply for data filtering include filtering by rules, language models and translation models. We also conduct several experiments to validate the effectiveness of training techniques. According to our experiments, the Annealing Adam optimizing function and ensemble decoding are the most effective techniques for the model training.

We build parallel feature decay algorithms (parfda) Moses statistical machine translation (SMT) models for language pairs in the translation task. parfda obtains results close to the top constrained phrase-based SMT with an average of 2.252 BLEU points difference on WMT 2017 datasets using significantly less computation for building SMT systems than that would be spent using all available corpora. We obtain BLEU upper bounds based on target coverage to identify which systems used additional data. We use PRO for tuning to decrease fluctuations in the results and postprocess translation outputs to decrease translation errors due to the casing of words. F1 scores on the key phrases of the English to Turkish testsuite that we prepared reveal that parfda achieves 2nd best results. Truecasing translations before scoring obtained the best results overall.

In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for Finnish-English and Estonian-English within the multi-lingual subtrack. All of our primary submissions implement an attention-based Neural Machine Translation architecture. Given that Finnish and Estonian belong to the same language family and are similar, we use as training data the combination of the datasets of both language pairs to paliate the data scarceness of each individual pair. We also report the translation quality of systems trained on individual language pair data to serve as baseline and comparison reference.

This paper describes the University of Tartu’s submission to the unsupervised machine translation track of WMT18 news translation shared task. We build several baseline translation systems for both directions of the English-Estonian language pair using monolingual data only; the systems belong to the phrase-based unsupervised machine translation paradigm where we experimented with phrase lengths of up to 3. As a main contribution, we performed a set of standalone experiments with compositional phrase embeddings as a substitute for phrases as individual vocabulary entries. Results show that reasonable n-gram vectors can be obtained by simply summing up individual word vectors which retains or improves the performance of phrase-based unsupervised machine tranlation systems while avoiding limitations of atomic phrase vectors.

This paper describes the submission systems of Alibaba for WMT18 shared news translation task. We participated in 5 translation directions including English ↔ Russian, English ↔ Turkish in both directions and English → Chinese. Our systems are based on Google’s Transformer model architecture, into which we integrated the most recent features from the academic research. We also employed most techniques that have been proven effective during the past WMT years, such as BPE, back translation, data selection, model ensembling and reranking, at industrial scale. For some morphologically-rich languages, we also incorporated linguistic knowledge into our neural network. For the translation tasks in which we have participated, our resulting systems achieved the best case sensitive BLEU score in all 5 directions. Notably, our English → Russian system outperformed the second reranked system by 5 BLEU score.

This paper describes the unsupervised neural machine translation (NMT) systems of the RWTH Aachen University developed for the English ↔ German news translation task of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). Our work is based on iterative back-translation using a shared encoder-decoder NMT model. We extensively compare different vocabulary types, word embedding initialization schemes and optimization methods for our model. We also investigate gating and weight normalization for the word embedding layer.

This article describes the Aalto University entry to the WMT18 News Translation Shared Task. We participate in the multilingual subtrack with a system trained under the constrained condition to translate from English to both Finnish and Estonian. The system is based on the Transformer model. We focus on improving the consistency of morphological segmentation for words that are similar orthographically, semantically, and distributionally; such words include etymological cognates, loan words, and proper names. For this, we introduce Cognate Morfessor, a multilingual variant of the Morfessor method. We show that our approach improves the translation quality particularly for Estonian, which has less resources for training the translation model.

This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT18 evaluation campaign. This year, we examined the developments and additions to popular neural machine translation toolkits and measure improvements in performance on the Russian–English language pair.

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

This paper describes the Neural Machine Translation (NMT) system of TencentFmRD for Chinese↔English news translation tasks of WMT 2018. Our systems are neural machine translation systems trained with our original system TenTrans. TenTrans is an improved NMT system based on Transformer self-attention mechanism. In addition to the basic settings of Transformer training, TenTrans uses multi-model fusion techniques, multiple features reranking, different segmentation models and joint learning. Finally, we adopt some data selection strategies to fine-tune the trained system and achieve a stable performance improvement. Our Chinese→English system achieved the second best BLEU scores and fourth best cased BLEU scores among all WMT18 submitted systems.

This paper describes the statistical machine translation system built by the MLLP research group of Universitat Politècnica de València for the German→English news translation shared task of the EMNLP 2018 Third Conference on Machine Translation (WMT18). We used an ensemble of Transformer architecture–based neural machine translation systems. To train our system under “constrained” conditions, we filtered the provided parallel data with a scoring technique using character-based language models, and we added parallel data based on synthetic source sentences generated from the provided monolingual corpora.

This paper describes the Microsoft submission to the WMT2018 news translation shared task. We participated in one language direction – English-German. Our system follows current best-practice and combines state-of-the-art models with new data filtering (dual conditional cross-entropy filtering) and sentence weighting methods. We trained fairly standard Transformer-big models with an updated version of Edinburgh’s training scheme for WMT2017 and experimented with different filtering schemes for Paracrawl. According to automatic metrics (BLEU) we reached the highest score for this subtask with a nearly 2 BLEU point margin over the next strongest system. Based on human evaluation we ranked first among constrained systems. We believe this is mostly caused by our data filtering/weighting regime.

We participated in the WMT 2018 shared news translation task in three language pairs: English-Estonian, English-Finnish, and English-Czech. Our main focus was the low-resource language pair of Estonian and English for which we utilized Finnish parallel data in a simple method. We first train a “parent model” for the high-resource language pair followed by adaptation on the related low-resource language pair. This approach brings a substantial performance boost over the baseline system trained only on Estonian-English parallel data. Our systems are based on the Transformer architecture. For the English to Czech translation, we have evaluated our last year models of hybrid phrase-based approach and neural machine translation mainly for comparison purposes.

We report on the efforts of the Johns Hopkins University to develop neural machine translation systems for the shared task for news translation organized around the Conference for Machine Translation (WMT) 2018. We developed systems for German–English, English– German, and Russian–English. Our novel contributions are iterative back-translation and fine-tuning on test sets from prior years.

In the current work, we present a description of the system submitted to WMT 2018 News Translation Shared task. The system was created to translate news text from Finnish to English. The system used a Character Based Neural Machine Translation model to accomplish the given task. The current paper documents the preprocessing steps, the description of the submitted system and the results produced using the same. Our system garnered a BLEU score of 12.9.

This paper presents the NICT’s participation to the WMT18 shared news translation task. We participated in the eight translation directions of four language pairs: Estonian-English, Finnish-English, Turkish-English and Chinese-English. For each translation direction, we prepared state-of-the-art statistical (SMT) and neural (NMT) machine translation systems. Our NMT systems were trained with the transformer architecture using the provided parallel data enlarged with a large quantity of back-translated monolingual data that we generated with a new incremental training framework. Our primary submissions to the task are the result of a simple combination of our SMT and NMT systems. Our systems are ranked first for the Estonian-English and Finnish-English language pairs (constraint) according to BLEU-cased.

This paper describes the PROMT submissions for the WMT 2018 Shared News Translation Task. This year we participated only in the English-Russian language pair. We built two primary neural networks-based systems: 1) a pure Marian-based neural system and 2) a hybrid system which incorporates OpenNMT-based neural post-editing component into our RBMT engine. We also submitted pure rule-based translation (RBMT) for contrast. We show competitive results with both primary submissions which significantly outperform the RBMT baseline.

This paper describes NTT’s neural machine translation systems submitted to the WMT 2018 English-German and German-English news translation tasks. Our submission has three main components: the Transformer model, corpus cleaning, and right-to-left n-best re-ranking techniques. Through our experiments, we identified two keys for improving accuracy: filtering noisy training sentences and right-to-left re-ranking. We also found that the Transformer model requires more training data than the RNN-based model, and the RNN-based model sometimes achieves better accuracy than the Transformer model when the corpus is small.

We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German. The core of our systems is the encoder-decoder based neural machine translation models using the transformer architecture. We enhanced the model with a deeper architecture. By using techniques to limit the memory consumption, we were able to train models that are 4 times larger on one GPU and improve the performance by 1.2 BLEU points. Furthermore, we performed sentence selection for the newly available ParaCrawl corpus. Thereby, we could improve the effectiveness of the corpus by 0.5 BLEU points.

The paper describes the development process of the Tilde’s NMT systems that were submitted for the WMT 2018 shared task on news translation. We describe the data filtering and pre-processing workflows, the NMT system training architectures, and automatic evaluation results. For the WMT 2018 shared task, we submitted seven systems (both constrained and unconstrained) for English-Estonian and Estonian-English translation directions. The submitted systems were trained using Transformer models.

We describe our NMT system submitted to the WMT2018 shared task in news translation. Our system is based on the Transformer model (Vaswani et al., 2017). We use an improved technique of backtranslation, where we iterate the process of translating monolingual data in one direction and training an NMT model for the opposite direction using synthetic parallel data. We apply a simple but effective filtering of the synthetic data. We pre-process the input sentences using coreference resolution in order to disambiguate the gender of pro-dropped personal pronouns. Finally, we apply two simple post-processing substitutions on the translated output. Our system is significantly (p < 0.05) better than all other English-Czech and Czech-English systems in WMT2018.

This paper describes the University of Helsinki’s submissions to the WMT18 shared news translation task for English-Finnish and English-Estonian, in both directions. This year, our main submissions employ a novel neural architecture, the Transformer, using the open-source OpenNMT framework. Our experiments couple domain labeling and fine tuned multilingual models with shared vocabularies between the source and target language, using the provided parallel data of the shared task and additional back-translations. Finally, we compare, for the English-to-Finnish case, the effectiveness of different machine translation architectures, starting from a rule-based approach to our best neural model, analyzing the output and highlighting future research.

This paper describes the statistical machine translation systems developed at RWTH Aachen University for the German→English, English→Turkish and Chinese→English translation tasks of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). We use ensembles of neural machine translation systems based on the Transformer architecture. Our main focus is on the German→English task where we to all automatic scored first with respect metrics provided by the organizers. We identify data selection, fine-tuning, batch size and model dimension as important hyperparameters. In total we improve by 6.8% BLEU over our last year’s submission and by 4.8% BLEU over the winning system of the 2017 German→English task. In English→Turkish task, we show 3.6% BLEU improvement over the last year’s winning system. We further report results on the Chinese→English task where we improve 2.2% BLEU on average over our baseline systems but stay behind the 2018 winning systems.

The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.

We describe LMU Munich’s unsupervised machine translation systems for English↔German translation. These systems were used to participate in the WMT18 news translation shared task and more specifically, for the unsupervised learning sub-track. The systems are trained on English and German monolingual data only and exploit and combine previously proposed techniques such as using word-by-word translated data based on bilingual word embeddings, denoising and on-the-fly backtranslation.

We participated in the WMT 2018 shared news translation task on English↔Chinese language pair. Our systems are based on attentional sequence-to-sequence models with some form of recursion and self-attention. Some data augmentation methods are also introduced to improve the translation performance. The best translation result is obtained with ensemble and reranking techniques. Our Chinese→English system achieved the highest cased BLEU score among all 16 submitted systems, and our English→Chinese system ranked the third out of 18 submitted systems.

This paper describes the submission of the NiuTrans neural machine translation system for the WMT 2018 Chinese ↔ English news translation tasks. Our baseline systems are based on the Transformer architecture. We further improve the translation performance 2.4-2.6 BLEU points from four aspects, including architectural improvements, diverse ensemble decoding, reranking, and post-processing. Among constrained submissions, we rank 2nd out of 16 submitted systems on Chinese → English task and 3rd out of 16 on English → Chinese task, respectively.

This paper describes the University of Maryland’s submission to the WMT 2018 Chinese↔English news translation tasks. Our systems are BPE-based self-attentional Transformer networks with parallel and backtranslated monolingual training data. Using ensembling and reranking, we improve over the Transformer baseline by +1.4 BLEU for Chinese→English and +3.97 BLEU for English→Chinese on newstest2017. Our best systems reach BLEU scores of 24.4 for Chinese→English and 39.0 for English→Chinese on newstest2018.

We present the results of automatic evaluation of discourse in machine translation (MT) outputs using the EVALD tool. EVALD was originally designed and trained to assess the quality of human writing, for native speakers and foreign-language learners. MT has seen a tremendous leap in translation quality at the level of sentences and it is thus interesting to see if the human-level evaluation is becoming relevant.

Progress in the quality of machine translation output calls for new automatic evaluation procedures and metrics. In this paper, we extend the Morpheval protocol introduced by Burlot and Yvon (2017) for the English-to-Czech and English-to-Latvian translation directions to three additional language pairs, and report its use to analyze the results of WMT 2018’s participants for these language pairs. Considering additional, typologically varied source and target languages also enables us to draw some generalizations regarding this morphology-oriented evaluation procedure.

We present a pilot study of machine translation of selected grammatical contrasts between Czech and English in WMT18 News Translation Task. For each phenomenon, we run a dedicated test which checks if the candidate translation expresses the phenomenon as expected or not. The proposed type of analysis is not an evaluation in the strict sense because the phenomenon can be correctly translated in various ways and we anticipate only one. What is nevertheless interesting are the differences between various MT systems and the single reference translation in their general tendency in handling the given phenomenon.

We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition. We work with a test suite specifically designed to assess system quality in various fine-grained categories known to be problematic. The main evaluation scores come from a semi-automatic process, combining automatic reference matching with extensive manual annotation of uncertain cases. We find that current NMT systems are good at translating pronouns with intra-sentential reference, but the inter-sentential cases remain difficult. NMT systems are also good at the translation of event pronouns, unlike systems from the phrase-based SMT paradigm. No single system performs best at translating all types of anaphoric pronouns, suggesting unexplained random effects influencing the translation of pronouns with NMT.

We present an analysis of 16 state-of-the-art MT systems on German-English based on a linguistically-motivated test suite. The test suite has been devised manually by a team of language professionals in order to cover a broad variety of linguistic phenomena that MT often fails to translate properly. It contains 5,000 test sentences covering 106 linguistic phenomena in 14 categories, with an increased focus on verb tenses, aspects and moods. The MT outputs are evaluated in a semi-automatic way through regular expressions that focus only on the part of the sentence that is relevant to each phenomenon. Through our analysis, we are able to compare systems based on their performance on these categories. Additionally, we reveal strengths and weaknesses of particular systems and we identify grammatical phenomena where the overall performance of MT is relatively low.

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

This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previous multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions ranked first for English→French and second for English→German language pairs among the constrained submissions according to the automatic evaluation metric METEOR.

This paper describes the MeMAD project entry to the WMT Multimodal Machine Translation Shared Task. We propose adapting the Transformer neural machine translation (NMT) architecture to a multi-modal setting. In this paper, we also describe the preliminary experiments with text-only translation systems leading us up to this choice. We have the top scoring system for both English-to-German and English-to-French, according to the automatic metrics for flickr18. Our experiments show that the effect of the visual features in our system is small. Our largest gains come from the quality of the underlying text-only NMT system. We find that appropriate use of additional data is effective.

AFRL-Ohio State extends its usage of visual domain-driven machine translation for use as a peer with traditional machine translation systems. As a peer, it is enveloped into a system combination of neural and statistical MT systems to present a composite translation.

We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features in the model: first, we include the image representation as another input to the network; second, we train the model to predict the visual features and use it as an auxiliary objective. For our submission, we acquired both textual and multimodal additional data. Both of the proposed methods yield significant improvements over recurrent networks and self-attentive textual baselines.

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.

This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation. In this paper, we introduce a simple approach to incorporate image information by feeding image features to the decoder side. We also explore different sequence level training methods including scheduled sampling and reinforcement learning which lead to substantial improvements. Our systems ensemble several models using different architectures and training methods and achieve the best performance for three subtasks: En-De and En-Cs in task 1 and (En+De+Fr)-Cs task 1B.

For the WMT 2018 shared task of translating documents pertaining to the Biomedical domain, we developed a scoring formula that uses an unsophisticated and effective method of weighting term frequencies and was integrated in a data selection pipeline. The method was applied on five language pairs and it performed best on Portuguese-English, where a BLEU score of 41.84 placed it third out of seven runs submitted by three institutions. In this paper, we describe our method and results with a special focus on Spanish-English where we compare it against a state-of-the-art method. Our contribution to the task lies in introducing a fast, unsupervised method for selecting domain-specific data for training models which obtain good results using only 10% of the general domain data.

This paper describes the system of Fraunhofer FOKUS for the WMT 2018 biomedical translation task. Our approach, described here, was to automatically select the most promising translation from a set of candidates produced with NMT (Transformer) models. We selected the highest fidelity translation of each sentence by using a dictionary, stemming and a set of heuristics. Our method is simple, can use any machine translators, and requires no further training in addition to that already employed to build the NMT models. The downside is that the score did not increase over the best in ensemble, but was quite close to it (difference about 0.5 BLEU).

We present the LMU Munich machine translation systems for the English–German language pair. We have built neural machine translation systems for both translation directions (English→German and German→English) and for two different domains (the biomedical domain and the news domain). The systems were used for our participation in the WMT18 biomedical translation task and in the shared task on machine translation of news. The main focus of our recent system development efforts has been on achieving improvements in the biomedical domain over last year’s strong biomedical translation engine for English→German (Huck et al., 2017a). Considerable progress has been made in the latter task, which we report on in this paper.

This paper describes the submission of Hunter Neural Machine Translation (NMT) to the WMT’18 Biomedical translation task from English to French. The discrepancy between training and test data distribution brings a challenge to translate text in new domains. Beyond the previous work of combining in-domain with out-of-domain models, we found accuracy and efficiency gain in combining different in-domain models. We conduct extensive experiments on NMT with transfer learning. We train on different in-domain Biomedical datasets one after another. That means parameters of the previous training serve as the initialization of the next one. Together with a pre-trained out-of-domain News model, we enhanced translation quality with 3.73 BLEU points over the baseline. Furthermore, we applied ensemble learning on training models of intermediate epochs and achieved an improvement of 4.02 BLEU points over the baseline. Overall, our system is 11.29 BLEU points above the best system of last year on the EDP 2017 test set.

This paper describes the machine translation systems developed by the Universidade Federal do Rio Grande do Sul (UFRGS) team for the biomedical translation shared task. Our systems are based on statistical machine translation and neural machine translation, using the Moses and OpenNMT toolkits, respectively. We participated in four translation directions for the English/Spanish and English/Portuguese language pairs. To create our training data, we concatenated several parallel corpora, both from in-domain and out-of-domain sources, as well as terminological resources from UMLS. Our systems achieved the best BLEU scores according to the official shared task evaluation.

The Transformer architecture has become the state-of-the-art in Machine Translation. This model, which relies on attention-based mechanisms, has outperformed previous neural machine translation architectures in several tasks. In this system description paper, we report details of training neural machine translation with multi-source Romance languages with the Transformer model and in the evaluation frame of the biomedical WMT 2018 task. Using multi-source languages from the same family allows improvements of over 6 BLEU points.

This paper presents the results of the WMT18 Metrics Shared Task. We asked participants of this task to score the outputs of the MT systems involved in the WMT18 News Translation Task with automatic metrics. We collected scores of 10 metrics and 8 research groups. In addition to that, we computed scores of 8 standard metrics (BLEU, SentBLEU, chrF, NIST, WER, PER, TER and CDER) as baselines. The collected scores were evaluated in terms of system-level correlation (how well each metric’s scores correlate with WMT18 official manual ranking of systems) and in terms of segment-level correlation (how often a metric agrees with humans in judging the quality of a particular sentence relative to alternate outputs). This year, we employ a single kind of manual evaluation: direct assessment (DA).

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.

We present the results from the fourth round of the WMT shared task on MT Automatic Post-Editing. The task consists in automatically correcting the output of a “black-box” machine translation system by learning from human corrections. Keeping the same general evaluation setting of the three previous rounds, this year we focused on one language pair (English-German) and on domain-specific data (Information Technology), with MT outputs produced by two different paradigms: phrase-based (PBSMT) and neural (NMT). Five teams submitted respectively 11 runs for the PBSMT subtask and 10 runs for the NMT subtask. In the former subtask, characterized by original translations of lower quality, top results achieved impressive improvements, up to -6.24 TER and +9.53 BLEU points over the baseline “do-nothing” system. The NMT subtask proved to be more challenging due to the higher quality of the original translations and the availability of less training data. In this case, top results show smaller improvements up to -0.38 TER and +0.8 BLEU points.

We posed the shared task of assigning sentence-level quality scores for a very noisy corpus of sentence pairs crawled from the web, with the goal of sub-selecting 1% and 10% of high-quality data to be used to train machine translation systems. Seventeen participants from companies, national research labs, and universities participated in this task.

In machine translation evaluation, a good candidate translation can be regarded as a paraphrase of the reference. We notice that some words are always copied during paraphrasing, which we call copy knowledge. Considering the stability of such knowledge, a good candidate translation should contain all these words appeared in the reference sentence. Therefore, in this participation of the WMT’2018 metrics shared task we introduce a simple statistical method for copy knowledge extraction, and incorporate it into Meteor metric, resulting in a new machine translation metric Meteor++. Our experiments show that Meteor++ can nicely integrate copy knowledge and improve the performance significantly on WMT17 and WMT15 evaluation sets.

The paper presents our participation in the WMT 2018 Metrics Shared Task. We propose an improved version of Translation Edit/Error Rate (TER). In addition to including the basic edit operations in TER, namely - insertion, deletion, substitution and shift, our metric also allows stem matching, optimizable edit costs and better normalization so as to correlate better with human judgement scores. The proposed metric shows much higher correlation with human judgments than TER.

We introduce the RUSE metric for the WMT18 metrics shared task. Sentence embeddings can capture global information that cannot be captured by local features based on character or word N-grams. Although training sentence embeddings using small-scale translation datasets with manual evaluation is difficult, sentence embeddings trained from large-scale data in other tasks can improve the automatic evaluation of machine translation. We use a multi-layer perceptron regressor based on three types of sentence embeddings. The experimental results of the WMT16 and WMT17 datasets show that the RUSE metric achieves a state-of-the-art performance in both segment- and system-level metrics tasks with embedding features only.

The paper presents our participation in the WMT 2018 shared task on word level quality estimation (QE) of machine translated (MT) text, i.e., to predict whether a word in MT output for a given source context is correctly translated and hence should be retained in the post-edited translation (PE), or not. To perform the QE task, we measure the similarity of the source context of the target MT word with the context for which the word is retained in PE in the training data. This is achieved in two different ways, using Bag-of-Words (BoW) model and Document-to-Vector (Doc2Vec) model. In the BoW model, we compute the cosine similarity while in the Doc2Vec model we consider the Doc2Vec similarity. By applying the Kneedle algorithm on the F1mult vs. similarity score plot, we derive the threshold based on which OK/BAD decisions are taken for the MT words. Experimental results revealed that the Doc2Vec model performs better than the BoW model on the word level QE task.

With improved prediction combination using weights based on their training performance and stacking and multilayer perceptrons to build deeper prediction models, RTMs become the 3rd system in general at the sentence-level prediction of translation scores and achieve the lowest RMSE in English to German NMT QET results. For the document-level task, we compare document-level RTM models with sentence-level RTM models obtained with the concatenation of document sentences and obtain similar results.

A huge amount of valuable resources is available on the web in English, which are often translated into local languages to facilitate knowledge sharing among local people who are not much familiar with English. However, translating such content manually is very tedious, costly, and time-consuming process. To this end, machine translation is an efficient approach to translate text without any human involvement. Neural machine translation (NMT) is one of the most recent and effective translation technique amongst all existing machine translation systems. In this paper, we apply NMT for English-Tamil language pair. We propose a novel neural machine translation technique using word-embedding along with Byte-Pair-Encoding (BPE) to develop an efficient translation system that overcomes the OOV (Out Of Vocabulary) problem for languages which do not have much translations available online. We use the BLEU score for evaluating the system performance. Experimental results confirm that our proposed MIDAS translator (8.33 BLEU score) outperforms Google translator (3.75 BLEU score).

In this paper, a novel approach to Quality Estimation is introduced, which extends the method in (Duma and Menzel, 2017) by also considering pseudo-reference translations as data sources to the tree and sequence kernels used before. Two variants of the system were submitted to the sentence level WMT18 Quality Estimation Task for the English-German language pair. They have been ranked 4th and 6th out of 13 systems in the SMT track, while in the NMT track ranks 4 and 5 out of 11 submissions have been reached.

We describe Vicomtech’s participation in the WMT 2018 shared task on quality estimation, for which we submitted minimalist quality estimators. The core of our approach is based on two simple features: lexical translation overlaps and language model cross-entropy scores. These features are exploited in two system variants: uMQE is an unsupervised system, where the final quality score is obtained by averaging individual feature scores; sMQE is a supervised variant, where the final score is estimated by a Support Vector Regressor trained on the available annotated datasets. The main goal of our minimalist approach to quality estimation is to provide reliable estimators that require minimal deployment effort, few resources, and, in the case of uMQE, do not depend on costly data annotation or post-editing. Our approach was applied to all language pairs in sentence quality estimation, obtaining competitive results across the board.

The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and which are wrong. In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach. The first part uses an embedding layer to represent words and their part-of-speech tags in both languages. The second part leverages a one-dimensional convolution layer to integrate local context information for each target word. The third part applies a stack of feed-forward and recurrent neural networks to further encode the global context in the sentence before making the predictions. This model was submitted as the CMU entry to the WMT2018 shared task on QE, and achieves strong results, ranking first in three of the six tracks.

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.

We describe the Universitat d’Alacant submissions to the word- and sentence-level machine translation (MT) quality estimation (QE) shared task at WMT 2018. Our approach to word-level MT QE builds on previous work to mark the words in the machine-translated sentence as OK or BAD, and is extended to determine if a word or sequence of words need to be inserted in the gap after each word. Our sentence-level submission simply uses the edit operations predicted by the word-level approach to approximate TER. The method presented ranked first in the sub-task of identifying insertions in gaps for three out of the six datasets, and second in the rest of them.

The goal of WMT 2018 Shared Task on Translation Quality Estimation is to investigate automatic methods for estimating the quality of machine translation results without reference translations. This paper presents the QE Brain system, which proposes the neural Bilingual Expert model as a feature extractor based on conditional target language model with a bidirectional transformer and then processes the semantic representations of source and the translation output with a Bi-LSTM predictive model for automatic quality estimation. The system has been applied to the sentence-level scoring and ranking tasks as well as the word-level tasks for finding errors for each word in translations. An extensive set of experimental results have shown that our system outperformed the best results in WMT 2017 Quality Estimation tasks and obtained top results in WMT 2018.

This paper describes the submissions of the team from the University of Tartu for the sentence-level Quality Estimation shared task of WMT18. The proposed models use features based on attention weights of a neural machine translation system and cross-lingual phrase embeddings as input features of a regression model. Two of the proposed models require only a neural machine translation system with an attention mechanism with no additional resources. Results show that combining neural networks and baseline features leads to significant improvements over the baseline features alone.

This paper describes the Microsoft and University of Edinburgh submission to the Automatic Post-editing shared task at WMT2018. Based on training data and systems from the WMT2017 shared task, we re-implement our own models from the last shared task and introduce improvements based on extensive parameter sharing. Next we experiment with our implementation of dual-source transformer models and data selection for the IT domain. Our submissions decisively wins the SMT post-editing sub-task establishing the new state-of-the-art and is a very close second (or equal, 16.46 vs 16.50 TER) in the NMT sub-task. Based on the rather weak results in the NMT sub-task, we hypothesize that neural-on-neural APE might not be actually useful.

This paper presents our English–German Automatic Post-Editing (APE) system submitted to the APE Task organized at WMT 2018 (Chatterjee et al., 2018). The proposed model is an extension of the transformer architecture: two separate self-attention-based encoders encode the machine translation output (mt) and the source (src), followed by a joint encoder that attends over a combination of these two encoded sequences (encsrc and encmt) for generating the post-edited sentence. We compare this multi-source architecture (i.e, {src, mt} → pe) to a monolingual transformer (i.e., mt → pe) model and an ensemble combining the multi-source {src, mt} → pe and single-source mt → pe models. For both the PBSMT and the NMT task, the ensemble yields the best results, followed by the multi-source model and last the single-source approach. Our best model, the ensemble, achieves a BLEU score of 66.16 and 74.22 for the PBSMT and NMT task, respectively.

This paper presents the Automatic Post-editing (APE) systems submitted by the DFKI-MLT group to the WMT’18 APE shared task. Three monolingual neural sequence-to-sequence APE systems were trained using target-language data only: one using an attentional recurrent neural network architecture and two using the attention-only (transformer) architecture. The training data was composed of machine translated (MT) output used as source to the APE model aligned with their manually post-edited version or reference translation as target. We made use of the provided training sets only and trained APE models applicable to phrase-based and neural MT outputs. Results show better performances reached by the attention-only model over the recurrent one, significant improvement over the baseline when post-editing phrase-based MT output but degradation when applied to neural MT output.

This paper describes the POSTECH’s submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network. We modified the encoder-decoder attention to reflect the relation between the machine translation output, the source and the post-edited translation in APE problem. Experiments on WMT17 English-German APE data set show an improvement in both TER and BLEU score over the best result of WMT17 APE shared task. Our primary submission achieves -4.52 TER and +6.81 BLEU score on PBSMT task and -0.13 TER and +0.40 BLEU score for NMT task compare to the baseline.

Recent approaches to the Automatic Post-editing (APE) of Machine Translation (MT) have shown that best results are obtained by neural multi-source models that correct the raw MT output by also considering information from the corresponding source sentence. To this aim, we present for the first time a neural multi-source APE model based on the Transformer architecture. Moreover, we employ sequence-level loss functions in order to avoid exposure bias during training and to be consistent with the automatic evaluation metrics used for the task. These are the main features of our submissions to the WMT 2018 APE shared task, where we participated both in the PBSMT subtask (i.e. the correction of MT outputs from a phrase-based system) and in the NMT subtask (i.e. the correction of neural outputs). In the first subtask, our system improves over the baseline up to -5.3 TER and +8.23 BLEU points ranking second out of 11 submitted runs. In the second one, characterized by the higher quality of the initial translations, we report lower but statistically significant gains (up to -0.38 TER and +0.8 BLEU), ranking first out of 10 submissions.

Our entry to the parallel corpus filtering task uses a two-step strategy. The first step uses a series of pragmatic hard ‘rules’ to remove the worst example sentences. This first step reduces the effective corpus size down from the initial 1 billion to 160 million tokens. The second step uses four different heuristics weighted to produce a score that is then used for further filtering down to 100 or 10 million tokens. Our final system produces competitive results without requiring excessive fine tuning to the exact task or language pair. The first step in isolation provides a very fast filter that gives most of the gains of the final system.

We describe Vicomtech’s participation in the WMT 2018 Shared Task on parallel corpus filtering. We aimed to evaluate a simple approach to the task, which can efficiently process large volumes of data and can be easily deployed for new datasets in different language pairs and domains. We based our approach on STACC, an efficient and portable method for parallel sentence identification in comparable corpora. To address the specifics of the corpus filtering task, which features significant volumes of noisy data, the core method was expanded with a penalty based on the amount of unknown words in sentence pairs. Additionally, we experimented with a complementary data saturation method based on source sentence n-grams, with the goal of demoting parallel sentence pairs that do not contribute significant amounts of yet unobserved n-grams. Our approach requires no prior training and is highly efficient on the type of large datasets featured in the corpus filtering task. We achieved competitive results with this simple and portable method, ranking in the top half among competing systems overall.

A hybrid pipeline comprising rules and machine learning is used to filter a noisy web English-German parallel corpus for the Parallel Corpus Filtering task. The core of the pipeline is a module based on the logistic regression algorithm that returns the probability that a translation unit is accepted. The training set for the logistic regression is created by automatic annotation. The quality of the automatic annotation is estimated by manually labeling the training set.

The WMT 2018 Parallel Corpus Filtering Task aims to test various methods of filtering a noisy parallel corpus, to make it useful for training machine translation systems. We describe the AFRL submissions, including their preprocessing methods and quality metrics. Numerical results indicate relative benefits of different options and show where our methods are competitive.

This paper describes the participation of Webinterpret in the shared task on parallel corpus filtering at the Third Conference on Machine Translation (WMT 2018). The paper describes the main characteristics of our approach and discusses the results obtained on the data sets published for the shared task.

In this paper we describe LMU Munich’s submission for the WMT 2018 Parallel Corpus Filtering shared task which addresses the problem of cleaning noisy parallel corpora. The task of mining and cleaning parallel sentences is important for improving the quality of machine translation systems, especially for low-resource languages. We tackle this problem in a fully unsupervised fashion relying on bilingual word embeddings created without any bilingual signal. After pre-filtering noisy data we rank sentence pairs by calculating bilingual sentence-level similarities and then remove redundant data by employing monolingual similarity as well. Our unsupervised system achieved good performance during the official evaluation of the shared task, scoring only a few BLEU points behind the best systems, while not requiring any parallel training data.

In this work we introduce dual conditional cross-entropy filtering for noisy parallel data. For each sentence pair of the noisy parallel corpus we compute cross-entropy scores according to two inverse translation models trained on clean data. We penalize divergent cross-entropies and weigh the penalty by the cross-entropy average of both models. Sorting or thresholding according to these scores results in better subsets of parallel data. We achieve higher BLEU scores with models trained on parallel data filtered only from Paracrawl than with models trained on clean WMT data. We further evaluate our method in the context of the WMT2018 shared task on parallel corpus filtering and achieve the overall highest ranking scores of the shared task, scoring top in three out of four subtasks.

This work describes our submission to the WMT18 Parallel Corpus Filtering shared task. We use a slightly modified version of the Zipporah Corpus Filtering toolkit (Xu and Koehn, 2017), which computes an adequacy score and a fluency score on a sentence pair, and use a weighted sum of the scores as the selection criteria. This work differs from Zipporah in that we experiment with using the noisy corpus to be filtered to compute the combination weights, and thus avoids generating synthetic data as in standard Zipporah.

The WMT18 shared task on parallel corpus filtering (Koehn et al., 2018b) challenged teams to score sentence pairs from a large high-recall, low-precision web-scraped parallel corpus (Koehn et al., 2018a). Participants could use existing sample corpora (e.g. past WMT data) as a supervisory signal to learn what a “clean” corpus looks like. However, in lower-resource situations it often happens that the target corpus of the language is the only sample of parallel text in that language. We therefore made several unsupervised entries, setting ourselves an additional constraint that we not utilize the additional clean parallel corpora. One such entry fairly consistently scored in the top ten systems in the 100M-word conditions, and for one task—translating the European Medicines Agency corpus (Tiedemann, 2009)—scored among the best systems even in the 10M-word conditions.

We present our semantic textual similarity approach in filtering a noisy web crawled parallel corpus using YiSi—a novel semantic machine translation evaluation metric. The systems mainly based on this supervised approach perform well in the WMT18 Parallel Corpus Filtering shared task (4th place in 100-million-word evaluation, 8th place in 10-million-word evaluation, and 6th place overall, out of 48 submissions). In fact, our best performing system—NRC-yisi-bicov is one of the only four submissions ranked top 10 in both evaluations. Our submitted systems also include some initial filtering steps for scaling down the size of the test corpus and a final redundancy removal step for better semantic and token coverage of the filtered corpus. In this paper, we also describe our unsuccessful attempt in automatically synthesizing a noisy parallel development corpus for tuning the weights to combine different parallelism and fluency features.

This paper describes the Alibaba Machine Translation Group submissions to the WMT 2018 Shared Task on Parallel Corpus Filtering. While evaluating the quality of the parallel corpus, the three characteristics of the corpus are investigated, i.e. 1) the bilingual/translation quality, 2) the monolingual quality and 3) the corpus diversity. Both rule-based and model-based methods are adapted to score the parallel sentence pairs. The final parallel corpus filtering system is reliable, easy to build and adapt to other language pairs.

We present the UTFPR systems at the WMT 2018 parallel corpus filtering task. Our supervised approach discerns between good and bad translations by training classic binary classification models over an artificially produced binary classification dataset derived from a high-quality translation set, and a minimalistic set of 6 semantic distance features that rely only on easy-to-gather resources. We rank translations by their probability for the “good” label. Our results show that logistic regression pairs best with our approach, yielding more consistent results throughout the different settings evaluated.

This paper describes the submission of the Institute for Language and Speech Processing/Athena Research and Innovation Center (ILSP/ARC) for the WMT 2018 Parallel Corpus Filtering shared task. We explore several properties of sentences and sentence pairs that our system explored in the context of the task with the purpose of clustering sentence pairs according to their appropriateness in training MT systems. We also discuss alternative methods for ranking the sentence pairs of the most appropriate clusters with the aim of generating the two datasets (of 10 and 100 million words as required in the task) that were evaluated. By summarizing the results of several experiments that were carried out by the organizers during the evaluation phase, our submission achieved an average BLEU score of 26.41, even though it does not make use of any language-specific resources like bilingual lexica, monolingual corpora, or MT output, while the average score of the best participant system was 27.91.

This paper describes the participation of SYSTRAN to the shared task on parallel corpus filtering at the Third Conference on Machine Translation (WMT 2018). We participate for the first time using a neural sentence similarity classifier which aims at predicting the relatedness of sentence pairs in a multilingual context. The paper describes the main characteristics of our approach and discusses the results obtained on the data sets published for the shared task.

The paper describes parallel corpus filtering methods that allow reducing noise of noisy “parallel” corpora from a level where the corpora are not usable for neural machine translation training (i.e., the resulting systems fail to achieve reasonable translation quality; well below 10 BLEU points) up to a level where the trained systems show decent (over 20 BLEU points on a 10 million word dataset and up to 30 BLEU points on a 100 million word dataset). The paper also documents Tilde’s submissions to the WMT 2018 shared task on parallel corpus filtering.

This paper describes the submission of RWTH Aachen University for the De→En parallel corpus filtering task of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). We use several rule-based, heuristic methods to preselect sentence pairs. These sentence pairs are scored with count-based and neural systems as language and translation models. In addition to single sentence-pair scoring, we further implement a simple redundancy removing heuristic. Our best performing corpus filtering system relies on recurrent neural language models and translation models based on the transformer architecture. A model trained on 10M randomly sampled tokens reaches a performance of 9.2% BLEU on newstest2018. Using our filtering and ranking techniques we achieve 34.8% BLEU.

This paper describes Prompsit Language Engineering’s submissions to the WMT 2018 parallel corpus filtering shared task. Our four submissions were based on an automatic classifier for identifying pairs of sentences that are mutual translations. A set of hand-crafted hard rules for discarding sentences with evident flaws were applied before the classifier. We explored different strategies for achieving a training corpus with diverse vocabulary and fluent sentences: language model scoring, an active-learning-inspired data selection algorithm and n-gram saturation. Our submissions were very competitive in comparison with other participants on the 100 million word training corpus.

This paper presents the NICT’s participation in the WMT18 shared parallel corpus filtering task. The organizers provided 1 billion words German-English corpus crawled from the web as part of the Paracrawl project. This corpus is too noisy to build an acceptable neural machine translation (NMT) system. Using the clean data of the WMT18 shared news translation task, we designed several features and trained a classifier to score each sentence pairs in the noisy data. Finally, we sampled 100 million and 10 million words and built corresponding NMT systems. Empirical results show that our NMT systems trained on sampled data achieve promising performance.