摘要

1. Imitation Attacks and Defenses for Black-box Machine Translation Systems [PDF] 返回目录
EMNLP 2020. Long Paper
Eric Wallace, Mitchell Stern, Dawn Song
Adversaries may look to steal or attack black-box NLP systems, either for financial gain or to exploit model errors. One setting of particular interest is machine translation (MT), where models have high commercial value and errors can be costly. We investigate possible exploitations of black-box MT systems and explore a preliminary defense against such threats. We first show that MT systems can be stolen by querying them with monolingual sentences and training models to imitate their outputs. Using simulated experiments, we demonstrate that MT model stealing is possible even when imitation models have different input data or architectures than their target models. Applying these ideas, we train imitation models that reach within 0.6 BLEU of three production MT systems on both high-resource and low-resource language pairs. We then leverage the similarity of our imitation models to transfer adversarial examples to the production systems. We use gradient-based attacks that expose inputs which lead to semantically-incorrect translations, dropped content, and vulgar model outputs. To mitigate these vulnerabilities, we propose a defense that modifies translation outputs in order to misdirect the optimization of imitation models. This defense degrades the adversary's BLEU score and attack success rate at some cost in the defender's BLEU and inference speed.

2. Shallow-to-Deep Training for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, Jingbo Zhu
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we investigate the behavior of a well-tuned deep Transformer system. We find that stacking layers is helpful in improving the representation ability of NMT models and adjacent layers perform similarly. This inspires us to develop a shallow-to-deep training method that learns deep models by stacking shallow models. In this way, we successfully train a Transformer system with a 54-layer encoder. Experimental results on WMT’16 English-German and WMT’14 English-French translation tasks show that it is 1:4

3. CSP: Code-Switching Pre-training for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Zhen Yang, Bojie Hu, ambyera han, shen huang, Qi Ju
This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which randomly masks some fragments of the input sentence, the proposed CSP randomly replaces some words in the source sentence with their translation words in the target language. Specifically, we firstly perform lexicon induction with unsupervised word embedding mapping between the source and target languages, and then randomly replace some words in the input sentence with their translation words according to the extracted translation lexicons. CSP adopts the encoder-decoder framework: its encoder takes the code-mixed sentence as input, and its decoder predicts the replaced fragment of the input sentence. In this way, CSP is able to pre-train the NMT model by explicitly making the most of the alignment information extracted from the source and target monolingual corpus. Additionally, we relieve the pretrain-finetune discrepancy caused by the artificial symbols like [mask]. To verify the effectiveness of the proposed method, we conduct extensive experiments on unsupervised and supervised NMT. Experimental results show that CSP achieves significant improvements over baselines without pre-training or with other pre-training methods.

4. Non-Autoregressive Machine Translation with Latent Alignments [PDF] 返回目录
EMNLP 2020. Long Paper
Chitwan Saharia, William Chan, Saurabh Saxena, Mohammad Norouzi
This paper presents two strong methods, CTC and Imputer, for non-autoregressivemachine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a simple CTC model can achieve state-of-the-art for single-step non-autoregressive machine translation, contrary to what prior work indicates. In addition, we adapt the Imputer model for non-autoregressive machine translation and demonstrate that Imputer with just 4 generation steps can match the performance of an autoregressive Transformer baseline.Our latent alignment models are simpler than many existing non-autoregressive translation baselines; for example, we do not require target length prediction or re-scoring with an autoregressive model.On the competitive WMT'14 En$\rightarrow$De task, our CTC model achieves 25.7 BLEU with a single generation step, while Imputer achieves 27.5 BLEU with 2 generation steps, and 28.0 BLEU with 4 generation steps. This compares favourably to the autoregressive Transformer baseline at 27.8 BLEU.

5. Language Model Prior for Low-Resource Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Christos Baziotis, Barry Haddow, Alexandra Birch
The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel approach to incorporate a LM as prior in a neural translation model (TM). Specifically, we add a regularization term, which pushes the output distributions of the TM to be probable under the LM prior, while avoiding wrong predictions when the TM "disagrees" with the LM. This objective relates to knowledge distillation, where the LM can be viewed as teaching the TM about the target language. The proposed approach does not compromise decoding speed, because the LM is used only at training time, unlike previous work that requires it during inference. We present an analysis of the effects that different methods have on the distributions of the TM. Results on two low-resource machine translation datasets show clear improvements even with limited monolingual data.

6. Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Maximiliana Behnke, Kenneth Heafield
The attention mechanism is the crucial component of the transformer architecture. Recent research shows that most attention heads are not confident in their decisions and can be pruned. However, removing them before training a model results in lower quality. In this paper, we apply the lottery ticket hypothesis to prune heads in the early stages of training. Our experiments on machine translation show that it is possible to remove up to three-quarters of attention heads from transformer-big during early training with an average -0.1 change in BLEU for Turkish→English. The pruned model is 1.5 times as fast at inference, albeit at the cost of longer training. Our method is complementary to other approaches, such as teacher-student, with English→German student model gaining an additional 10% speed-up with 75% encoder attention removed and 0.2 BLEU loss.

7. Translationese in Machine Translation Evaluation [PDF] 返回目录
EMNLP 2020. Long Paper
Yvette Graham, Barry Haddow, Philipp Koehn
The term translationese has been used to describe features of translated text, and in this paper, we provide detailed analysis of potential adverse effects of translationese on machine translation evaluation.Our analysis shows differences in conclusions drawn from evaluations that include translationese in test data compared to experiments that tested only with text originally composed in that language. For this reason we recommend that reverse-created test data be omitted from future machine translation test sets. In addition, we provide a re-evaluation of a past machine translation evaluation claiming human-parity of MT. One important issue not previously considered is statistical power of significance tests applied to comparison of human and machine translation. Since the very aim of past evaluations was investigation of ties between human and MT systems, power analysis is of particular importance, to avoid, for example, claims of human parity simply corresponding to Type II error resulting from the application of a low powered test. We provide detailed analysis of tests used in such evaluations to provide an indication of a suitable minimum sample size for future studies.

8. Towards Enhancing Faithfulness for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Rongxiang Weng, Heng Yu, Xiangpeng Wei, Weihua Luo
Neural machine translation (NMT) has achieved great success due to the ability to generate high-quality sentences. Compared with human translations, one of the drawbacks of current NMT is that translations are not usually faithful to the input, e.g., omitting information or generating unrelated fragments, which inevitably decreases the overall quality, especially for human readers. In this paper, we propose a novel training strategy with a multi-task learning paradigm to build a faithfulness enhanced NMT model (named \textscFEnmt). During the NMT training process, we sample a subset from the training set and translate them to get fragments that have been mistranslated. Afterward, the proposed multi-task learning paradigm is employed on both encoder and decoder to guide NMT to correctly translate these fragments. Both automatic and human evaluations verify that our \textscFEnmt could improve translation quality by effectively reducing unfaithful translations.

9. Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing [PDF] 返回目录
EMNLP 2020. Long Paper
Brian Thompson, Matt Post
We frame the task of machine translation evaluation as one of scoring machine translation output with a sequence-to-sequence paraphraser, conditioned on a human reference. We propose training the paraphraser as a multilingual NMT system, treating paraphrasing as a zero-shot translation task (e.g., Czech to Czech). This results in the paraphraser’s output mode being centered around a copy of the input sequence, which represents the best case scenario where the MT system output matches a human reference. Our method is simple and intuitive, and does not require human judgements for training. Our single model (trained in 39 languages) outperforms or statistically ties with all prior metrics on the WMT 2019 segment-level shared metrics task in all languages (excluding Gujarati where the model had no training data). We also explore using our model for the task of quality estimation as a metric—conditioning on the source instead of the reference—and find that it significantly outperforms every submission to the WMT 2019 shared task on quality estimation in every language pair.

10. Uncertainty-Aware Semantic Augmentation for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Luxi Xing, Weihua Luo
As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for NMT only observe one of them from the parallel corpora for the model training but have to deal with adequate variations under the same meaning at inference. This leads to a discrepancy of the data distribution between the training and the inference phases. To address this problem, we propose uncertainty-aware semantic augmentation, which explicitly captures the universal semantic information among multiple semantically-equivalent source sentences and enhances the hidden representations with this information for better translations. Extensive experiments on various translation tasks reveal that our approach significantly outperforms the strong baselines and the existing methods.

11. Iterative Domain-Repaired Back-Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Hao-Ran Wei, Zhirui Zhang, Boxing Chen, Weihua Luo
In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent.One common and effective strategy for this case is exploiting in-domain monolingual data with the back-translation method.However, the synthetic parallel data is very noisy because they are generated by imperfect out-of-domain systems, resulting in the poor performance of domain adaptation.To address this issue, we propose a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair (DR) model to refine translations in synthetic bilingual data. To this end, we construct corresponding data for the DR model training by round-trip translating the monolingual sentences, and then design the unified training framework to optimize paired DR and NMT models jointly.Experiments on adapting NMT models between specific domains and from the general domain to specific domains demonstrate the effectiveness of our proposed approach, achieving 15.79 and 4.47 BLEU improvements on average over unadapted models and back-translation.

12. Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Dana Ruiter, Josef van Genabith, Cristina España-Bonet
Self-supervised neural machine translation (SSNMT) jointly learns to identify and select suitable training data from comparable (rather than parallel) corpora and to translate, in a way that the two tasks support each other in a virtuous circle. In this study, we provide an in-depth analysis of the sampling choices the SSNMT model makes during training. We show how, without it having been told to do so, the model self-selects samples of increasing (i) complexity and(ii) task-relevance in combination with (iii) performing a denoising curriculum. We observe that the dynamics of the mutual-supervision signals of both system internal representation types are vital for the extraction and translation performance. We show that in terms of the Gunning-Fog Readability index, SSNMT starts extracting and learning from Wikipedia data suitable for high school students and quickly moves towards content suitable for first year undergraduate students.

13. Simultaneous Machine Translation with Visual Context [PDF] 返回目录
EMNLP 2020. Long Paper
Ozan Caglayan, Julia Ive, Veneta Haralampieva, Pranava Madhyastha, Loïc Barrault, Lucia Specia
Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is read progressively, creating the need for anticipation. In this paper, we seek to understand whether the addition of visual information can compensate for the missing source context. To this end, we analyse the impact of different multimodal approaches and visual features on state-of-the-art SiMT frameworks. Our results show that visual context is helpful and that visually-grounded models based on explicit object region information are much better than commonly used global features, reaching up to 3 BLEU points improvement under low latency scenarios. Our qualitative analysis illustrates cases where only the multimodal systems are able to translate correctly from English into gender-marked languages, as well as deal with differences in word order, such as adjective-noun placement between English and French.

14. Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Jason Lee, Raphael Shu, Kyunghyun Cho
We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et al., 2020), we train an inference network to approximate the gradient of the marginal log probability of the target sentence, using the latent variable instead. This allows us to use gradient-based optimization to find the target sentence at inference time that approximately maximizes its marginal probability. As each refinement step only involves computation in the latent space of low dimensionality (we use 8 in our experiments), we avoid computational overhead incurred by existing non-autoregressive inference procedures that often refine in token space. We compare our approach to a recently proposed EM-like inference procedure (Shu et al., 2020) that optimizes in a hybrid space, consisting of both discrete and continuous variables. We evaluate our approach on WMT’14 En→De, WMT’16 Ro→En and IWSLT’16 De→En, and observe two advantages over the EM-like inference: (1) it is computationally efficient, i.e. each refinement step is twice as fast, and (2) it is more effective, resulting in higher marginal probabilities and BLEU scores with the same number of refinement steps. On WMT’14 En→De, for instance, our approach is able to decode 6.2 times faster than the autoregressive model with minimal degradation to translation quality (0.9 BLEU).

15. Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning [PDF] 返回目录
EMNLP 2020. Long Paper
Xiaomian Kang, Yang Zhao, Jiajun Zhang, Chengqing Zong
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different sizes of context. To address this problem, we propose an effective approach to select dynamic context so that the document-level translation model can utilize the more useful selected context sentences to produce better translations. Specifically, we introduce a selection module that is independent of the translation module to score each candidate context sentence. Then, we propose two strategies to explicitly select a variable number of context sentences and feed them into the translation module. We train the two modules end-to-end via reinforcement learning. A novel reward is proposed to encourage the selection and utilization of dynamic context sentences. Experiments demonstrate that our approach can select adaptive context sentences for different source sentences, and significantly improves the performance of document-level translation methods.

16. Dynamic Data Selection and Weighting for Iterative Back-Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Zi-Yi Dou, Antonios Anastasopoulos, Graham Neubig
Back-translation has proven to be an effective method to utilize monolingual data in neural machine translation (NMT), and iteratively conducting back-translation can further improve the model performance. Selecting which monolingual data to back-translate is crucial, as we require that the resulting synthetic data are of high quality and reflect the target domain. To achieve these two goals, data selection and weighting strategies have been proposed, with a common practice being to select samples close to the target domain but also dissimilar to the average general-domain text. In this paper, we provide insights into this commonly used approach and generalize it to a dynamic curriculum learning strategy, which is applied to iterative back-translation models. In addition, we propose weighting strategies based on both the current quality of the sentence and its improvement over the previous iteration. We evaluate our models on domain adaptation, low-resource, and high-resource MT settings and on two language pairs. Experimental results demonstrate that our methods achieve improvements of up to~1.8 BLEU points over competitive baselines.

17. Multi-task Learning for Multilingual Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Yiren Wang, ChengXiang Zhai, Hany Hassan
While monolingual data has been shown to be useful in improving bilingual neural machine translation (NMT), effectively and efficiently leveraging monolingual data for Multilingual NMT (MNMT) systems is a less explored area. In this work, we propose a multi-task learning (MTL) framework that jointly trains the model with the translation task on bitext data and two denoising tasks on the monolingual data. We conduct extensive empirical studies on MNMT systems with $10$ language pairs from WMT datasets. We show that the proposed approach can effectively improve the translation quality for both high-resource and low-resource languages with large margin, achieving significantly better results than the individual bilingual models. We also demonstrate the efficacy of the proposed approach in the zero-shot setup for language pairs without bitext training data. Furthermore, we show the effectiveness of MTL over pre-training approaches for both NMT and cross-lingual transfer learning NLU tasks; the proposed approach outperforms massive scale models trained on single task.

18. Accurate Word Alignment Induction from Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Yun Chen, Yang Liu, Guanhua Chen, Xin Jiang, Qun Liu
Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights do capture accurate word alignments and propose two novel word alignment induction methods Shift-Att and Shift-AET. The main idea is to induce alignments at the step when the to-be-aligned target token is the decoder input rather than the decoder output as in previous work. Shift-Att is an interpretation method that induces alignments from the attention weights of Transformer and does not require parameter update or architecture change. Shift-AET extracts alignments from an additional alignment module which is tightly integrated into Transformer and trained in isolation with supervision from symmetrized Shift-Att alignments. Experiments on three publicly available datasets demonstrate that both methods perform better than their corresponding neural baselines and Shift-AET significantly outperforms GIZA++ by 1.4-4.8 AER points.

19. Token-level Adaptive Training for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Shuhao Gu, Jinchao Zhang, Fandong Meng, Yang Feng, Wanying Xie, Jie Zhou, Dong Yu
There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT). The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution. However, low-frequency tokens may carry critical semantic information that will affect the translation quality once they are neglected. In this paper, we explored target token-level adaptive objectives based on token frequencies to assign appropriate weights for each target token during training. We aimed that those meaningful but relatively low-frequency words could be assigned with larger weights in objectives to encourage the model to pay more attention to these tokens. Our method yields consistent improvements in translation quality on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens where we can get 1.68, 1.02, and 0.52 BLEU increases compared with baseline, respectively. Further analyses show that our method can also improve the lexical diversity of translation.

20. Multi-Unit Transformers for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Jianhao Yan, Fandong Meng, Jie Zhou
Transformer models achieve remarkable success in Neural Machine Translation. Many efforts have been devoted to deepening the Transformer by stacking several units (i.e., a combination of Multihead Attentions and FFN) in a cascade, while the investigation over multiple parallel units draws little attention. In this paper, we propose the Multi-Unit Transformer (MUTE) , which aim to promote the expressiveness of the Transformer by introducing diverse and complementary units. Specifically, we use several parallel units and show that modeling with multiple units improves model performance and introduces diversity. Further, to better leverage the advantage of the multi-unit setting, we design biased module and sequential dependency that guide and encourage complementariness among different units. Experimental results on three machine translation tasks, the NIST Chinese-to-English, WMT'14 English-to-German and WMT'18 Chinese-to-English, show that the MUTE models significantly outperform the Transformer-Base, by up to +1.52, +1.90 and +1.10 BLEU points, with only a mild drop in inference speed (about 3.1\%). In addition, our methods also surpass the Transformer-Big model, with only 54\% of its parameters. These results demonstrate the effectiveness of the MUTE, as well as its efficiency in both the inference process and parameter usage.

21. Translation Artifacts in Cross-lingual Transfer Learning [PDF] 返回目录
EMNLP 2020. Long Paper
Mikel Artetxe, Gorka Labaka, Eneko Agirre
Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test set or the training set is a widely used transfer technique. In this paper, we show that such translation process can introduce subtle artifacts that have a notable impact in existing cross-lingual models. For instance, in natural language inference, translating the premise and the hypothesis independently can reduce the lexical overlap between them, which current models are highly sensitive to. We show that some previous findings in cross-lingual transfer learning need to be reconsidered in the light of this phenomenon. Based on the gained insights, we also improve the state-of-the-art in XNLI for the translate-test and zero-shot approaches by 4.3 and 2.8 points, respectively.

22. Towards Detecting and Exploiting Disambiguation Biases in Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Denis Emelin, Ivan Titov, Rico Sennrich
Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found in training data, specifically superficial word co-occurrences, rather than a deeper understanding of the source text. We introduce a method for the prediction of disambiguation errors based on statistical data properties, demonstrating its effectiveness across several domains and model types. Moreover, we develop a simple adversarial attack strategy that minimally perturbs sentences in order to elicit disambiguation errors to further probe the robustness of translation models. Our findings indicate that disambiguation robustness varies substantially between domains and that different models trained on the same data are vulnerable to different attacks.

23. Direct Segmentation Models for Streaming Speech Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Javier Iranzo-Sánchez, Adrià Giménez Pastor, Joan Albert Silvestre-Cerdà, Pau Baquero-Arnal, Jorge Civera Saiz, Alfons Juan
The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by a segmenter that splits the ASR output into hopefully, semantically self-contained chunks to be fed into the MT system. This is specially challenging in the case of streaming ST, where latency requirements must also be taken into account. This work proposes novel segmentation models for streaming ST that incorporate not only textual, but also acoustic information to decide when the ASR output is split into a chunk. An extensive and throughly experimental setup is carried out on the Europarl-ST dataset to prove the contribution of acoustic information to the performance of the segmentation model in terms of BLEU score in a streaming ST scenario. Finally, comparative results with previous work also show the superiority of the segmentation models proposed in this work.

24. Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar
Despite being the seventh most widely spoken language in the world, Bengali has received much less attention in machine translation literature due to being low in resources. Most publicly available parallel corpora for Bengali are not large enough; and have rather poor quality, mostly because of incorrect sentence alignments resulting from erroneous sentence segmentation, and also because of a high volume of noise present in them. In this work, we build a customized sentence segmenter for Bengali and propose two novel methods for parallel corpus creation on low-resource setups: aligner ensembling and batch filtering. With the segmenter and the two methods combined, we compile a high-quality Bengali-English parallel corpus comprising of 2.75 million sentence pairs, more than 2 million of which were not available before. Training on neural models, we achieve an improvement of more than 9 BLEU score over previous approaches to Bengali-English machine translation. We also evaluate on a new test set of 1000 pairs made with extensive quality control. We release the segmenter, parallel corpus, and the evaluation set, thus elevating Bengali from its low-resource status. To the best of our knowledge, this is the first ever large scale study on Bengali-English machine translation. We believe our study will pave the way for future research on Bengali-English machine translation as well as other low-resource languages. Our data and code are available at https://github.com/csebuetnlp/banglanmt.

25. An Empirical Study of Generation Order for Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
William Chan, Mitchell Stern, Jamie Kiros, Jakob Uszkoreit
In this work, we present an empirical study of generation order for machine translation. Building on recent advances in insertion-based modeling, we first introduce a soft order-reward framework that enables us to train models to follow arbitrary oracle generation policies. We then make use of this framework to explore a large variety of generation orders, including uninformed orders, location-based orders, frequency-based orders, content-based orders, and model-based orders. Curiously, we find that for the WMT'14 English $\to$ German and WMT'18 English $\to$ Chinese translation tasks, order does not have a substantial impact on output quality. Moreover, for English $\to$ German, we even discover that unintuitive orderings such as alphabetical and shortest-first can match the performance of a standard Transformer, suggesting that traditional left-to-right generation may not be necessary to achieve high performance.

26. Distilling Multiple Domains for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Anna Currey, Prashant Mathur, Georgiana Dinu
Neural machine translation achieves impressive results in high-resource conditions, but performance often suffers when the input domain is low-resource. The standard practice of adapting a separate model for each domain of interest does not scale well in practice from both a quality perspective (brittleness under domain shift) as well as a cost perspective (added maintenance and inference complexity). In this paper, we propose a framework for training a single multi-domain neural machine translation model that is able to translate several domains without increasing inference time or memory usage. We show that this model can improve translation on both high- and low-resource domains over strong multi-domain baselines. In addition, our proposed model is effective when domain labels are unknown during training, as well as robust under noisy data conditions.

27. Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Wenxiang Jiao, Xing Wang, Shilin He, Irwin King, Michael Lyu, Zhaopeng Tu
Large-scale training datasets lie at the core of the recent success of neural machine translation (NMT) models. However, the complex patterns and potential noises in the large-scale data make training NMT models difficult. In this work, we explore to identify the inactive training examples which contribute less to the model performance, and show that the existence of inactive examples depends on the data distribution. We further introduce data rejuvenation to improve the training of NMT models on large-scale datasets by exploiting inactive examples. The proposed framework consists of three phases. First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities. Then, we train a rejuvenation model on the active examples, which is used to re-label the inactive examples with forward- translation. Finally, the rejuvenated examples and the active examples are combined to train the final NMT model. Experimental results on WMT14 English-German and English-French datasets show that the proposed data rejuvenation consistently and significantly improves performance for several strong NMT models. Extensive analyses reveal that our approach stabilizes and accelerates the training process of NMT models, resulting in final models with better generalization capability.

28. Bridging Linguistic Typology and Multilingual Machine Translation with Multi-view Language Representations [PDF] 返回目录
EMNLP 2020. Long Paper
Arturo Oncevay, Barry Haddow, Alexandra Birch
Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language characterisation. We propose to fuse both views using singular vector canonical correlation analysis and study what kind of information is induced from each source. By inferring typological features and language phylogenies, we observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy in tasks that require information about language similarities, such as language clustering and ranking candidates for multilingual transfer. With our method, we can easily project and assess new languages without expensive retraining of massive multilingual or ranking models, which are major disadvantages of related approaches.

29. Improving Word Sense Disambiguation with Translations [PDF] 返回目录
EMNLP 2020. Long Paper
Yixing Luan, Bradley Hauer, Lili Mou, Grzegorz Kondrak
It has been conjectured that multilingual information can help monolingual word sense disambiguation (WSD). However, existing WSD systems rarely consider multilingual information, and no effective method has been proposed for improving WSD by generating translations. In this paper, we present a novel approach that improves the performance of a base WSD system using machine translation. Since our approach is language independent, we perform WSD experiments on several languages. The results demonstrate that our methods can consistently improve the performance of WSD systems, and obtain state-ofthe-art results in both English and multilingual WSD. To facilitate the use of lexical translation information, we also propose BABALIGN, an precise bitext alignment algorithm which is guided by multilingual lexical correspondences from BabelNet.

30. PyMT5: Multi-mode Translation of Natural Language and Python Code with Transformers [PDF] 返回目录
EMNLP 2020. Long Paper
Colin Clement, Dawn Drain, Jonathan Timcheck, Alexey Svyatkovskiy, Neel Sundaresan
Simultaneously modeling source code and natural language has many exciting applications in automated software development and understanding. Pursuant to achieving such technology, we introduce PyMT5, the Python method text-to-text transfer transformer, which is trained to translate between all pairs of Python method feature combinations: a single model that can both predict whole methods from natural language documentation strings (docstrings) and summarize code into docstrings of any common style. We present an analysis and modeling effort of a large-scale parallel corpus of 26 million Python methods and 7.7 million method-docstring pairs, demonstrating that for docstring and method generation, PyMT5~ outperforms similarly-sized auto-regressive language models (GPT2) which were English pre-trained or randomly initialized. On the CodeSearchNet test set, our best model predicts 92.1% syntactically correct method bodies, achieved a BLEU score of 8.59 for method generation and 16.3 for docstring generation (summarization), and achieved a ROUGE-L F-score of 24.8 for method generation and 36.7 for docstring generation.

31. Learning Adaptive Segmentation Policy for Simultaneous Translation [PDF] 返回目录
EMNLP 2020. Long Paper
Ruiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu, Haifeng Wang
Balancing accuracy and latency is a great challenge for simultaneous translation. To achieve high accuracy, the model usually needs to wait for more streaming text before translation, which results in increased latency. However, keeping low latency would probably hurt accuracy. Therefore, it is essential to segment the ASR output into appropriate units for translation. Inspired by human interpreters, we propose a novel adaptive segmentation policy for simultaneous translation. The policy learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation. Experimental results on Chinese-English and German-English translation show that our method achieves a better accuracy-latency trade-off over recently proposed state-of-the-art methods.

32. ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization [PDF] 返回目录
EMNLP 2020. Long Paper
Shiyue Zhang, Benjamin Frey, Mohit Bansal
Cherokee is a highly endangered Native American language spoken by the Cherokee people. The Cherokee culture is deeply embedded in its language. However, there are approximately only 2,000 fluent first language Cherokee speakers remaining in the world and the number is declining every year. To help save this endangered language, we introduce ChrEn, a Cherokee-English parallel dataset, to facilitate machine translation research between Cherokee and English. Compared to some popular machine translation language pairs, ChrEn is extremely low-resource, only containing 14k sentence pairs in total. We split our parallel data in ways that facilitate both in-domain and out-of-domain evaluation. We also collect 5k Cherokee monolingual data to enable semi-supervised learning. Besides these datasets, we propose several Cherokee-English and English-Cherokee machine translation systems. We compare SMT (phrase-based) versus NMT (RNN-based and Transformer-based) systems; supervised versus semi-supervised (via language model, back-translation, and BERT/Multilingual-BERT) methods; as well as transfer learning versus multilingual joint training with 4 other languages. Our best results are 15.8/12.7 BLEU for in-domain and 6.5/5.0 BLEU for out-of-domain Chr-En/EnChr translations, respectively; and we hope that our dataset and systems will encourage future work by the community for Cherokee language revitalization.

33. Generating Diverse Translation from Model Distribution with Dropout [PDF] 返回目录
EMNLP 2020. Long Paper
Xuanfu Wu, Yang Feng, Chenze Shao
Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inference, the posterior model distribution can be approximated with a variational distribution, from which the final models for inference are sampled. We conducted experiments on Chinese-English and English-German translation tasks and the results shows that our method makes a better trade-off between diversity and accuracy.

34. Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information [PDF] 返回目录
EMNLP 2020. Long Paper
Zehui Lin, Xiao Pan, Mingxuan Wang, Xipeng Qiu, Jiangtao Feng, Hao Zhou, Lei Li
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach to pre-train a universal multilingual neural machine translation model. Our key idea in mRASP is its novel technique of random aligned substitution, which brings words and phrases with similar meanings across multiple languages closer in the representation space. We pre-train a mRASP model on 32 language pairs jointly with only public datasets. The model is then ﬁne-tuned on downstream language pairs to obtain specialized MT models. We carry out extensive experiments on 42 translation directions across a diverse settings, including low, medium, rich resource, and as well as transferring to exotic language pairs. Experimental results demonstrate that mRASP achieves signiﬁcant performance improvement compared to directly training on those target pairs. It is the ﬁrst time to verify that multiple lowresource language pairs can be utilized to improve rich resource MT. Surprisingly, mRASP is even able to improve the translation quality on exotic languages that never occur in the pretraining corpus. Code, data, and pre-trained models are available at https://github. com/linzehui/mRASP.

35. Self-Paced Learning for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Short Paper
Yu Wan, Baosong Yang, Derek F. Wong, Yikai Zhou, Lidia S. Chao, Haibo Zhang, Boxing Chen
Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such kind of curriculum learning rely on the quality of artificial schedule drawn up with the handcrafted features, e.g. sentence length or word rarity. We ameliorate this procedure with a more flexible manner by proposing self-paced learning, where NMT model is allowed to 1) automatically quantify the learning confidence over training examples; and 2) flexibly govern its learning via regulating the loss in each iteration step. Experimental results over multiple translation tasks demonstrate that the proposed model yields better performance than strong baselines and those models trained with human-designed curricula on both translation quality and convergence speed.

36. Simulated Multiple Reference Training Improves Low-Resource Machine Translation [PDF] 返回目录
EMNLP 2020. Short Paper
Huda Khayrallah, Brian Thompson, Matt Post, Philipp Koehn
Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT), a novel MT training method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a paraphraser and training the MT model to predict the paraphraser’s distribution over possible tokens. We demonstrate the effectiveness of SMRT in low-resource settings when translating to English, with improvements of 1.2 to 7.0 BLEU. We also find SMRT is complementary to back-translation.

37. On the Sparsity of Neural Machine Translation Models [PDF] 返回目录
EMNLP 2020. Short Paper
Yong Wang, Longyue Wang, Victor Li, Zhaopeng Tu
Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of computational resources. In response to this problem, we empirically investigate whether the redundant parameters can be reused to achieve better performance. Experiments and analyses are systematically conducted on different datasets and NMT architectures. We show that: 1) the pruned parameters can be rejuvenated to improve the baseline model by up to +0.8 BLEU points; 2) the rejuvenated parameters are reallocated to enhance the ability of modeling low-level lexical information.

38. Translation Quality Estimation by Jointly Learning to Score and Rank [PDF] 返回目录
EMNLP 2020. Short Paper
Jingyi Zhang, Josef van Genabith
The translation quality estimation (QE) task, particularly the QE as a Metric task, aims to evaluate the general quality of a translation based on the translation and the source sentence without using reference translations. Supervised learning of this QE task requires human evaluation of translation quality as training data. Human evaluation of translation quality can be performed in different ways, including assigning an absolute score to a translation or ranking different translations. In order to make use of different types of human evaluation data for supervised learning, we present a multi-task learning QE model that jointly learns two tasks: score a translation and rank two translations. Our QE model exploits cross-lingual sentence embeddings from pre-trained multilingual language models. We obtain new state-of-the-art results on the WMT 2019 QE as a Metric task and outperform sentBLEU on the WMT 2019 Metrics task.

39. Incorporating a Local Translation Mechanism into Non-autoregressive Translation [PDF] 返回目录
EMNLP 2020. Short Paper
Xiang Kong, Zhisong Zhang, Eduard Hovy
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among target outputs. Specifically, for each target decoding position, instead of only one token, we predict a short sequence of tokens in an autoregressive way. We further design an efficient merging algorithm to align and merge the output pieces into one final output sequence. We integrate LAT into the conditional masked language model (CMLM) (Ghazvininejad et al.,2019) and similarly adopt iterative decoding. Empirical results on five translation tasks show that compared with CMLM, our method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5x speedup. Further analysis indicates that our method reduces repeated translations and performs better at longer sentences. Our code will be released to the public.

40. Language Adapters for Zero Shot Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Short Paper
Jerin Philip, Alexandre Berard, Matthias Gallé, Laurent Besacier
We propose a novel adapter layer formalism for adapting multilingual models. They are more parameter-efficient than existing adapter layers while obtaining as good or better performance. The layers are specific to one language (as opposed to bilingual adapters) allowing to compose them and generalize to unseen language-pairs. In this zero-shot setting, they obtain a median improvement of +2.77 BLEU points over a strong 20-language multilingual Transformer baseline trained on TED talks.

41. Effectively Pretraining a Speech Translation Decoder with Machine Translation Data [PDF] 返回目录
EMNLP 2020. Short Paper
Ashkan Alinejad, Anoop Sarkar
Directly translating from speech to text using an end-to-end approach is still challenging for many language pairs due to insufficient data. Although pretraining the encoder parameters using the Automatic Speech Recognition (ASR) task improves the results in low resource settings, attempting to use pretrained parameters from the Neural Machine Translation (NMT) task has been largely unsuccessful in previous works. In this paper, we will show that by using an adversarial regularizer, we can bring the encoder representations of the ASR and NMT tasks closer even though they are in different modalities, and how this helps us effectively use a pretrained NMT decoder for speech translation.

42. Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Short Paper
Pei Zhang, Boxing Chen, Niyu Ge, Kai Fan
Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the baseline model. In this paper, we research extensively the pros and cons of the standard transformer in document-level translation, and find that the auto-regressive property can simultaneously bring both the advantage of the consistency and the disadvantage of error accumulation. Therefore, we propose a surprisingly simple long-short term masking self-attention on top of the standard transformer to both effectively capture the long-range dependence and reduce the propagation of errors. We examine our approach on the two publicly available document-level datasets. We can achieve a strong result in BLEU and capture discourse phenomena.

43. Fully Quantized Transformer for Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Gabriele Prato, Ella Charlaix, Mehdi Rezagholizadeh
State-of-the-art neural machine translation methods employ massive amounts of parameters. Drastically reducing computational costs of such methods without affecting performance has been up to this point unsuccessful. To this end, we propose FullyQT: an all-inclusive quantization strategy for the Transformer. To the best of our knowledge, we are the first to show that it is possible to avoid any loss in translation quality with a fully quantized Transformer. Indeed, compared to full-precision, our 8-bit models score greater or equal BLEU on most tasks. Comparing ourselves to all previously proposed methods, we achieve state-of-the-art quantization results.

44. Improving Grammatical Error Correction with Machine Translation Pairs [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Wangchunshu Zhou, Tao Ge, Chang Mu, Ke Xu, Furu Wei, Ming Zhou
We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models (e.g., Chinese to English) of different qualities (i.e., poor and good). The poor translation model can resemble the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and grammaticality, while the good translation model generally generates fluent and grammatically correct translations. With the pair of translation models, we can generate unlimited numbers of poor to good English sentence pairs from text in the source language (e.g., Chinese) of the translators. Our approach can generate various error-corrected patterns and nicely complement the other data synthesis approaches for GEC. Experimental results demonstrate the data generated by our approach can effectively help a GEC model to improve the performance and achieve the state-of-the-art single-model performance in BEA-19 and CoNLL-14 benchmark datasets.

45. Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Alessandro Raganato, Yves Scherrer, Jörg Tiedemann
Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different parts of the input. However, recent works have shown that most attention heads learn simple, and often redundant, positional patterns. In this paper, we propose to replace all but one attention head of each encoder layer with simple fixed – non-learnable – attentive patterns that are solely based on position and do not require any external knowledge. Our experiments with different data sizes and multiple language pairs show that fixing the attention heads on the encoder side of the Transformer at training time does not impact the translation quality and even increases BLEU scores by up to 3 points in low-resource scenarios.

46. Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Baohao Liao, Yingbo Gao, Hermann Ney
Mutual learning, where multiple agents learn collaboratively and teach one another, has been shown to be an effective way to distill knowledge for image classification tasks. In this paper, we extend mutual learning to the machine translation task and operate at both the sentence-level and the token-level. Firstly, we co-train multiple agents by using the same parallel corpora. After convergence, each agent selects and learns its poorly predicted tokens from other agents. The poorly predicted tokens are determined by the acceptance-rejection sampling algorithm. Our experiments show that sequential mutual learning at the sentence-level and the token-level improves the results cumulatively. Absolute improvements compared to strong baselines are obtained on various translation tasks. On the IWSLT’14 German-English task, we get a new state-of-the-art BLEU score of 37.0. We also report a competitive result, 29.9 BLEU score, on the WMT’14 English-German task.

47. Active Learning Approaches to Enhancing Neural Machine Translation: An Empirical Study [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Yuekai Zhao, Haoran Zhang, Shuchang Zhou, Zhihua Zhang
Active learning is an efficient approach for mitigating data dependency when training neural machine translation (NMT) models. In this paper, we explore new training frameworks by incorporating active learning into various techniques such as transfer learning and iterative back-translation (IBT) under a limited human translation budget. We design a word frequency based acquisition function and combine it with a strong uncertainty based method. The combined method steadily outperforms all other acquisition functions in various scenarios. As far as we know, we are the first to do a large-scale study on actively training Transformer for NMT. Specifically, with a human translation budget of only 20% of the original parallel corpus, we manage to surpass Transformer trained on the entire parallel corpus in three language pairs.

48. Adversarial Subword Regularization for Robust Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Jungsoo Park, Mujeen Sung, Jinhyuk Lee, Jaewoo Kang
Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword segmentations mostly relies on the pre-trained subword language models from which erroneous segmentations of unseen words are less likely to be sampled. In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. We experimentally show that our model-based adversarial samples effectively encourage NMT models to be less sensitive to segmentation errors and improve the performance of NMT models in low-resource and out-domain datasets.

49. Automatically Identifying Gender Issues in Machine Translation using Perturbations [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Hila Gonen, Kellie Webster
The successful application of neural methods to machine translation has realized huge quality advances for the community. With these improvements, many have noted outstanding challenges, including the modeling and treatment of gendered language. While previous studies have identified issues using synthetic examples, we develop a novel technique to mine examples from real world data to explore challenges for deployed systems. We use our method to compile an evaluation benchmark spanning examples for four languages from three language families, which we publicly release to facilitate research. The examples in our benchmark expose where model representations are gendered, and the unintended consequences these gendered representations can have in downstream application.

50. Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Weijia Xu, Xing Niu, Marine Carpuat
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared. We introduce a novel dual reconstruction objective that provides a unified view of Iterative Back-Translation and Dual Learning. It motivates a theoretical analysis and controlled empirical study on German-English and Turkish-English tasks, which both suggest that Iterative Back-Translation is more effective than Dual Learning despite its relative simplicity.

51. Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi Fasubaa, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddeen Muhammad, Salomon Kabongo Kabenamualu, Salomey Osei, Freshia Sackey, Rubungo Andre Niyongabo, Ricky Macharm, Perez Ogayo, Orevaoghene Ahia, Musie Meressa Berhe, Mofetoluwa Adeyemi, Masabata Mokgesi-Selinga, Lawrence Okegbemi, Laura Martinus, Kolawole Tajudeen, Kevin Degila, Kelechi Ogueji, Kathleen Siminyu, Julia Kreutzer, Jason Webster, Jamiil Toure Ali, Jade Abbott, Iroro Orife, Ignatius Ezeani, Idris Abdulkadir Dangana, Herman Kamper, Hady Elsahar, Goodness Duru, Ghollah Kioko, Murhabazi Espoir, Elan van Biljon, Daniel Whitenack, Christopher Onyefuluchi, Chris Chinenye Emezue, Bonaventure F. P. Dossou, Blessing Sibanda, Blessing Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, Abdallah Bashir
Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. ‘Low-resourced’-ness is a complex problem going beyond data availability and reflects systemic problems in society. In this paper, we focus on the task of Machine Translation (MT), that plays a crucial role for information accessibility and communication worldwide. Despite immense improvements in MT over the past decade, MT is centered around a few high-resourced languages. As MT researchers cannot solve the problem of low-resourcedness alone, we propose participatory research as a means to involve all necessary agents required in the MT development process. We demonstrate the feasibility and scalability of participatory research with a case study on MT for African languages. Its implementation leads to a collection of novel translation datasets, MT benchmarks for over 30 languages, with human evaluations for a third of them, and enables participants without formal training to make a unique scientific contribution. Benchmarks, models, data, code, and evaluation results are released at https://github.com/masakhane-io/masakhane-mt.

52. Computer Assisted Translation with Neural Quality Estimation and Auotmatic Post-Editing [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Ke Wang, Jiayi Wang, Niyu Ge, Yangbin Shi, Yu Zhao, Kai Fan
With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine translation systems and human translators needs to be manually closed by post-editing. In this paper, we propose an end-to-end deep learning framework of the quality estimation and automatic post-editing of the machine translation output. Our goal is to provide error correction suggestions and to further relieve the burden of human translators through an interpretable model. To imitate the behavior of human translators, we design three efficient delegation modules – quality estimation, generative post-editing, and atomic operation post-editing and construct a hierarchical model based on them. We examine this approach with the English–German dataset from WMT 2017 APE shared task and our experimental results can achieve the state-of-the-art performance. We also verify that the certified translators can significantly expedite their post-editing processing with our model in human evaluation.

53. On Romanization for Model Transfer Between Scripts in Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Chantal Amrhein, Rico Sennrich
Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.

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

55. PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Jiazhao Li, Corey Lester, Xinyan Zhao, Yuting Ding, Yun Jiang, V.G.Vinod Vydiswaran
The language used by physicians and health professionals in prescription directions includes medical jargon and implicit directives and causes much confusion among patients. Human intervention to simplify the language at the pharmacies may introduce additional errors that can lead to potentially severe health outcomes. We propose a novel machine translation-based approach, PharmMT, to automatically and reliably simplify prescription directions into patient-friendly language, thereby significantly reducing pharmacist workload. We evaluate the proposed approach over a dataset consisting of over 530K prescriptions obtained from a large mail-order pharmacy. The end-to-end system achieves a BLEU score of 60.27 against the reference directions generated by pharmacists, a 39.6% relative improvement over the rule-based normalization. Pharmacists judged 94.3% of the simplified directions as usable as-is or with minimal changes. This work demonstrates the feasibility of a machine translation-based tool for simplifying prescription directions in real-life.

56. Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu, Sheng Zhong
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented graph-structured input and decodes a tree-structured output. In particular, we investigated our model for solving two problems, neural semantic parsing and math word problem. Our extensive experiments demonstrate that our Graph2Tree model outperforms or matches the performance of other state-of-the-art models on these tasks.

57. On Long-Tailed Phenomena in Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Vikas Raunak, Siddharth Dalmia, Vivek Gupta, Florian Metze
State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens, tackling which remains a major challenge. The analysis of long-tailed phenomena in the context of structured prediction tasks is further hindered by the added complexities of search during inference. In this work, we quantitatively characterize such long-tailed phenomena at two levels of abstraction, namely, token classification and sequence generation. We propose a new loss function, the Anti-Focal loss, to better adapt model training to the structural dependencies of conditional text generation by incorporating the inductive biases of beam search in the training process. We show the efficacy of the proposed technique on a number of Machine Translation (MT) datasets, demonstrating that it leads to significant gains over cross-entropy across different language pairs, especially on the generation of low-frequency words. We have released the code to reproduce our results.

58. A Multilingual View of Unsupervised Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Xavier Garcia, Pierre Foret, Thibault Sellam, Ankur Parikh
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where there is only monolingual data available, we propose a novel setup where one language in the (source, target) pair is not associated with any parallel data, but there may exist auxiliary parallel data that contains the other. This auxiliary data can naturally be utilized in our probabilistic framework via a novel cross-translation loss term. Empirically, we show that our approach results in higher BLEU scores over state-of-the-art unsupervised models on the WMT’14 English-French, WMT’16 English-German, and WMT’16 English-Romanian datasets in most directions.

59. KoBE: Knowledge-Based Machine Translation Evaluation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Zorik Gekhman, Roee Aharoni, Genady Beryozkin, Markus Freitag, Wolfgang Macherey
We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a large-scale multilingual knowledge base, and (2) measuring the recall of the grounded entities found in the candidate vs. those found in the source. Our approach achieves the highest correlation with human judgements on 9 out of the 18 language pairs from the WMT19 benchmark for evaluation without references, which is the largest number of wins for a single evaluation method on this task. On 4 language pairs, we also achieve higher correlation with human judgements than BLEU. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data.

60. Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Luyu Gao, Xinyi Wang, Graham Neubig
To improve the performance of Neural Machine Translation (NMT) for low-resource languages (LRL), one effective strategy is to leverage parallel data from a related high-resource language (HRL). However, multilingual data has been found more beneficial for NMT models that translate from the LRL to a target language than the ones that translate into the LRLs. In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate into the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft Decoupled Encoding (Wang et al., 2019), we propose DecSDE, an efficient character n-gram based embedding specifically designed for the NMT decoder. Our experiments show that DecSDE leads to consistent gains of up to 1.8 BLEU on translation from English to four different languages.

61. The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Jie He, Tao Wang, Deyi Xiong, Qun Liu
Does neural machine translation yield translations that are congenial with common sense? In this paper, we present a test suite to evaluate the commonsense reasoning capability of neural machine translation. The test suite consists of three test sets, covering lexical and contextless/contextual syntactic ambiguity that requires commonsense knowledge to resolve. We manually create 1,200 triples, each of which contain a source sentence and two contrastive translations, involving 7 different common sense types. Language models pretrained on large-scale corpora, such as BERT, GPT-2, achieve a commonsense reasoning accuracy of lower than 72% on target translations of this test suite. We conduct extensive experiments on the test suite to evaluate commonsense reasoning in neural machine translation and investigate factors that have impact on this capability. Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy ( 6 60.1%) and reasoning consistency (6 31%). We will release our test suite as a machine translation commonsense reasoning testbed to promote future work in this direction.

62. It’s not a Non-Issue: Negation as a Source of Error in Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Md Mosharaf Hossain, Antonios Anastasopoulos, Eduardo Blanco, Alexis Palmer
As machine translation (MT) systems progress at a rapid pace, questions of their adequacy linger. In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. We investigate whether translating negation is an issue for modern MT systems using 17 translation directions as test bed. Through thorough analysis, we find that indeed the presence of negation can significantly impact downstream quality, in some cases resulting in quality reductions of more than 60%. We also provide a linguistically motivated analysis that directly explains the majority of our findings. We release our annotations and code to replicate our analysis here: https://github.com/mosharafhossain/negation-mt.

63. Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang
Simultaneous speech-to-speech translation is an extremely challenging but widely useful scenario that aims to generate target-language speech only a few seconds behind the source-language speech. In addition, we have to continuously translate a speech of multiple sentences, but all recent solutions merely focus on the single-sentence scenario. As a result, current approaches will accumulate more and more latencies in later sentences when the speaker talks faster and introduce unnatural pauses into translated speech when the speaker talks slower. To overcome these issues, we propose Self-Adaptive Translation which flexibly adjusts the length of translations to accommodate different source speech rates. At similar levels of translation quality (as measured by BLEU), our method generates more fluent target speech latency than the baseline, in both Zh<->En directions.

64. Finding the Optimal Vocabulary Size for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Thamme Gowda, Jonathan May
We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others.

65. Reference Language based Unsupervised Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Zuchao Li, Hai Zhao, Rui Wang, Masao Utiyama, Eiichiro Sumita
Exploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enhancement delivered by the well-used pivot language in the absence of a source language to target language parallel corpus. The rise of unsupervised neural machine translation (UNMT) almost completely relieves the parallel corpus curse, though UNMT is still subject to unsatisfactory performance due to the vagueness of the clues available for its core back-translation training. Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism. Experimental results show that our methods improve the quality of UNMT over that of a strong baseline that uses only one auxiliary language, demonstrating the usefulness of the proposed reference language-based UNMT and establishing a good start for the community.

66. Assessing Human-Parity in Machine Translation on the Segment Level [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Yvette Graham, Christian Federmann, Maria Eskevich, Barry Haddow
Recent machine translation shared tasks have shown top-performing systems to tie or in some cases even outperform human translation. Such conclusions about system and human performance are, however, based on estimates aggregated from scores collected over large test sets of translations and unfortunately leave some remaining questions unanswered. For instance, simply because a system significantly outperforms the human translator on average may not necessarily mean that it has done so for every translation in the test set. Firstly, are there remaining source segments present in evaluation test sets that cause significant challenges for top-performing systems and can such challenging segments go unnoticed due to the opacity of current human evaluation procedures? To provide insight into these issues we carefully inspect the outputs of top-performing systems in the most recent WMT-19 news translation shared task for all language pairs in which a system either tied or outperformed human translation. Our analysis provides a new method of identifying the remaining segments for which either machine or human perform poorly. For example, in our close inspection of WMT-19 English to German and German to English we discover the segments that disjointly proved a challenge for human and machine. For English to Russian, there were no segments included in our sample of translations that caused a significant challenge for the human translator, while we again identify the set of segments that caused issues for the top-performing system.

67. Factorized Transformer for Multi-Domain Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Yongchao Deng, Hongfei Yu, Heng Yu, Xiangyu Duan, Weihua Luo
Multi-Domain Neural Machine Translation (NMT) aims at building a single system that performs well on a range of target domains. However, along with the extreme diversity of cross-domain wording and phrasing style, the imperfections of training data distribution and the inherent defects of the current sequential learning process all contribute to making the task of multi-domain NMT very challenging. To mitigate these problems, we propose the Factorized Transformer, which consists of an in-depth factorization of the parameters of an NMT model, namely Transformer in this paper, into two categories: domain-shared ones that encode common cross-domain knowledge and domain-specific ones that are private for each constituent domain. We experiment with various designs of our model and conduct extensive validations on English to French open multi-domain dataset. Our approach achieves state-of-the-art performance and opens up new perspectives for multi-domain and open-domain applications.

68. Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Shoetsu Sato, Jin Sakuma, Naoki Yoshinaga, Masashi Toyoda, Masaru Kitsuregawa
Neural network methods exhibit strong performance only in a few resource-rich domains. Practitioners therefore employ domain adaptation from resource-rich domains that are, in most cases, distant from the target domain. Domain adaptation between distant domains (e.g., movie subtitles and research papers), however, cannot be performed effectively due to mismatches in vocabulary; it will encounter many domain-specific words (e.g., “angstrom”) and words whose meanings shift across domains (e.g., “conductor”). In this study, aiming to solve these vocabulary mismatches in domain adaptation for neural machine translation (NMT), we propose vocabulary adaptation, a simple method for effective fine-tuning that adapts embedding layers in a given pretrained NMT model to the target domain. Prior to fine-tuning, our method replaces the embedding layers of the NMT model by projecting general word embeddings induced from monolingual data in a target domain onto a source-domain embedding space. Experimental results indicate that our method improves the performance of conventional fine-tuning by 3.86 and 3.28 BLEU points in En-Ja and De-En translation, respectively.

69. Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Qiang Wang, Tong Xiao, Jingbo Zhu
The standard neural machine translation model can only decode with the same depth configuration as training. Restricted by this feature, we have to deploy models of various sizes to maintain the same translation latency, because the hardware conditions on different terminal devices (e.g., mobile phones) may vary greatly. Such individual training leads to increased model maintenance costs and slower model iterations, especially for the industry. In this work, we propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference. Experimental results show that our approach can simultaneously support decoding in 24 depth configurations and is superior to the individual training and another flexible depth model training method——LayerDrop.

70. Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation [PDF] 返回目录
EMNLP 2020. Findings Short Paper
Insoo Chung, Byeongwook Kim, Yoonjung Choi, Se Jung Kwon, Yongkweon Jeon, Baeseong Park, Sangha Kim, Dongsoo Lee
The deployment of widely used Transformer architecture is challenging because of heavy computation load and memory overhead during inference, especially when the target device is limited in computational resources such as mobile or edge devices. Quantization is an effective technique to address such challenges. Our analysis shows that for a given number of quantization bits, each block of Transformer contributes to translation quality and inference computations in different manners. Moreover, even inside an embedding block, each word presents vastly different contributions. Correspondingly, we propose a mixed precision quantization strategy to represent Transformer weights by an extremely low number of bits (e.g., under 3 bits). For example, for each word in an embedding block, we assign different quantization bits based on statistical property. Our quantized Transformer model achieves 11.8× smaller model size than the baseline model, with less than -0.5 BLEU. We achieve 8.3× reduction in run-time memory footprints and 3.5× speed up (Galaxy N10+) such that our proposed compression strategy enables efficient implementation for on-device NMT.

注：论文列表使用AC论文搜索器整理！

WITH LOVE OF WORLD

【NLP】 EMNLP 2020 Neural Machine Translation 机器翻译相关论文整理

目录

摘要