https://github.com/niutrans/mt-paper-lists
MT paper lists (by conference)
https://github.com/niutrans/mt-paper-lists
machine-translation neural-machine-translation paper-list
Last synced: about 2 months ago
JSON representation
MT paper lists (by conference)
- Host: GitHub
- URL: https://github.com/niutrans/mt-paper-lists
- Owner: NiuTrans
- License: bsd-3-clause
- Created: 2019-06-17T04:59:31.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2020-12-07T07:32:52.000Z (over 4 years ago)
- Last Synced: 2025-01-08T18:12:08.941Z (3 months ago)
- Topics: machine-translation, neural-machine-translation, paper-list
- Homepage:
- Size: 95.7 KB
- Stars: 121
- Watchers: 18
- Forks: 52
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Papers!!!
- [List by Conference](#list-by-conference)
- [ACL](#acl)
- [2018](#2018)
- [2019](#2019)
- [2020](#2020)
- [EMNLP](#emnlp)
- [2018](#2018-1)
- [2019](#2019-1)
- [NAACL](#naacl)
- [2018](#2018-2)
- [2019](#2019-2)
- [AAAI](#aaai)
- [2020](#2020-1)
- [IJCAI](#ijcai)
- [2019](#2019-3)
- [COLING](#coling)
- [2018](#2018-3)
- [List by Area](#list-by-area)
- [Deep Transformer](#deep-transformer)
- [Fast RNN](#fast-rnn)
- [Knowledge Distillation of BERT](#knowledge-distillation-of-bert)
- [None Autoregressive Translation](#none-autoregressive-translation)
## List by Conference
### ACL
#### 2018
1. **Unsupervised Neural Machine Translation with Weight Sharing.** [paper](http://aclweb.org/anthology/P18-1005)
*Zhen Yang, Wei Chen, Feng Wang, Bo Xu*
**Domain**: Low-resource
2. **Triangular Architecture for Rare Language Translation.** [paper](http://aclweb.org/anthology/P18-1006)
*Shuo Ren, Wenhu Chen, Shujie Liu, Mu Li, Ming Zhou and Shuai Ma*
**Domain**: Low-resource
3. **On the Limitations of Unsupervised Bilingual Dictionary Induction.** [paper](http://aclweb.org/anthology/P18-1072)
*Anders Søgaard, Sebastian Ruder, Ivan Vulic*
**Domain**: Low-resource
4. **The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation.** [paper](https://aclweb.org/anthology/P18-1008)
*Mia Xu Chen, Orhan Firat, Ankur Bapna, Melvin Johnson, Wolfgang Macherey, George Foster, Llion Jones, Niki Parmar, Noam Shazeer, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Mike Schuster, Zhifeng Chen*
**Domain**: Neural Network Architecture
5. **Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings.** [paper](http://aclweb.org/anthology/P18-1164)
*Shaohui Kuang, Junhui Li, Antonio Branco, Weihua Luo, Deyi Xiong*
**Domain**: Neural Network Architecture
6. **Accelerating Neural Transformer via an Average Attention Network.** [paper](http://aclweb.org/anthology/P18-1166)
*Biao Zhang, Deyi Xiong, and Jinsong Su*
**Domain**: Neural Network Architecture
7. **Neural Hidden Markov Model for Machine Translation.** [paper](http://aclweb.org/anthology/P18-2060)
*Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan, Hermann Ney*
**Domain**: Neural Network Architecture
8. **Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates.** [paper](http://aclweb.org/anthology/P18-1007)
*Taku Kudo*
**Domain**: Robustness of NMT
9. **A Stochastic Decoder for Neural Machine Translation.** [paper](http://aclweb.org/anthology/P18-1115)
*Philip Schulz, Wilker Aziz, Trevor Cohn*
**Domain**: Robustness of NMT
10. **Forest-Based Neural Machine Translation.** [paper](http://aclweb.org/anthology/P18-1116)
*Chunpeng Ma, Akihiro Tamura, Masao Utiyama3, Tiejun Zhao1, Eiichiro Sumita3*
**Domain**: Robustness of NMT
11. **Towards Robust Neural Machine Translation.** [paper](http://aclweb.org/anthology/P18-1163)
*Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai and Yang Liu*
**Domain**: Robustness of NMT
#### 2019
1. **Latent Variable Model for Multi-modal Translation.** [paper](https://arxiv.org/abs/1811.00357)
*Iacer Calixto, Miguel Rios and Wilker Aziz*
**Domain**: Multimodal Translation
2. **Learning Deep Transformer Models for Machine Translation.** [paper](https://arxiv.org/abs/1906.01787)
*Qiang Wang, Bei Li, Tong Xiao, Jingbo Zhu, Changliang Li, Derek F. Wong and Lidia S. Chao*
**Domain**: Neural Network Architecture
3. **When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion.** [paper](https://arxiv.org/abs/1905.05979)
*Elena Voita, Rico Sennrich and Ivan Titov*
**Domain**: Context-aware NMT
4. **A Compact and Language-Sensitive Multilingual Translation Method.** [paper](-)
*Yining Wang, Long Zhou, Jiajun Zhang, Feifei Zhai, Jingfang Xu and Chengqing Zong*
**Domain**: Training
5. **Robust Neural Machine Translation with Doubly Adversarial Inputs.** [paper](https://arxiv.org/abs/1906.02443)
*Yong Cheng, Lu Jiang and Wolfgang Macherey*
**Domain**: Robustness of NMT
6. **Shared-Private Bilingual Word Embeddings for Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.03100)
*Xuebo Liu, Derek F. Wong, Yang Liu and Lidia S. Chao, Tong Xiao, Jingbo Zhu*
**Domain**: Practical Problems in Machine Translation
7. **Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation.** [paper](-)
*Viktor Hangya and Alexander Fraser*
**Domain**: Low-resource
8. **Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation.** [paper](-)
*Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita and Tiejun Zhao*
**Domain**: Low-resource
9. **Neural Machine Translation with Reordering Embeddings.** [paper](-)
*Kehai Chen, Rui Wang, Masao Utiyama and Eiichiro Sumita*
**Domain**: Training
10. **Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation.** [paper](-)
*Bram Bulte and Arda Tezcan*
**Domain**: Training
11. **Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies.** [paper](https://arxiv.org/abs/1905.05475)
*Yunsu Kim, Yingbo Gao and Hermann Ney*
**Domain**: Domain Adaptation
12. **Bridging the Gap between Training and Inference for Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.02448)
*Wen Zhang, Yang Feng, Fandong Meng, Di You and Qun Liu*
**Domain**: Training
13. **Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations.** [paper](https://arxiv.org/abs/1906.01181)
*Jiatao Gu, Yong Wang, Kyunghyun Cho and Victor O.K. Li*
**Domain**: Low-resource
14. **Lattice Transformer for Speech Translation.** [paper](https://arxiv.org/abs/1906.05551)
*Pei Zhang, Niyu Ge, Boxing Chen and Kai Fan*
**Domain**: Practical Problems in Machine Translation
15. **Generalized Data Augmentation for Low-Resource Translation.** [paper](https://arxiv.org/abs/1906.03785)
*Mengzhou Xia, Xiang Kong, Antonios Anastasopoulos and Graham Neubig*
**Domain**: Low-resource
16. **Syntactically Supervised Transformers for Faster Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.02780)
*Nader Akoury, Kalpesh Krishna and Mohit Iyyer*
**Domain**: Practical Problems in Machine Translation
17. **Unsupervised Pivot Translation for Distant Languages.** [paper](https://arxiv.org/abs/1906.02461)
*Yichong Leng, Xu Tan, Tao QIN, Xiang-Yang Li and Tie-Yan Liu*
**Domain**: Low-resource
18. **Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.01130)
*Wei Wang, Isaac Caswell and Ciprian Chelba*
**Domain**: Training
19. **On the Word Alignment from Neural Machine Translation.** [paper](-)
*Xintong Li, Guanlin Li, Lemao Liu, Max Meng and Shuming Shi*
**Domain**: Problem Analysis
20. **Imitation Learning for Non-Autoregressive Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.02041)
*Bingzhen Wei, Mingxuan Wang, Hao Zhou, Junyang Lin and Xu SUN*
**Domain**: Neural Network Architecture
21. **Monotonic Infinite Lookback Attention for Simultaneous Machine Translation.** [paper](https://arxiv.org/abs/1906.05218)
*Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, Chung-Cheng Chiu, Semih Yavuz, Ruoming Pang, Wei Li and Colin Raffel*
**Domain**: Neural Network Architecture
22. **Domain Adaptation of Neural Machine Translation by Lexicon Induction.** [paper](https://arxiv.org/abs/1906.00376)
*Junjie Hu, Mengzhou Xia, Graham Neubig and Jaime Carbonell*
**Domain**: Domain Adaptation
23. **Beyond BLEU:Training Neural Machine Translation with Semantic Similarity.** [paper](-)
*John Wieting, Taylor Berg-Kirkpatrick, Kevin Gimpel and Graham Neubig*
**Domain**: Problem Analysis
24. **An Effective Approach to Unsupervised Machine Translation.** [paper](https://arxiv.org/abs/1902.01313)
*Mikel Artetxe, Gorka Labaka and Eneko Agirre*
**Domain**: Low-resource
25. **Distilling Translations with Visual Awareness.** [paper](https://arxiv.org/pdf/1906.07701)
*Julia Ive, Pranava Madhyastha and Lucia Specia*
**Domain**: Multimodal Translation
26. **Reference Network for Neural Machine Translation.** [paper](-)
*Han Fu, Chenghao Liu and Jianling Sun*
**Domain**: Neural Network Architecture
27. **Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation.** [paper](-)
*Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen and Jie Zhou*
**Domain**: Problem Analysis
28. **Sparse Sequence-to-Sequence Models.** [paper](https://arxiv.org/abs/1905.05702)
*Ben Peters, Vlad Niculae, André F.T. Martins*
**Domain**: Neural Network Architecture
29. **Look Harder: A Neural Machine Translation Model with Hard Attention.** [paper](-)
*Sathish Reddy Indurthi, Insoo Chung and Sangha Kim*
**Domain**: Neural Network Architecture
30. **Robust Neural Machine Translation with Joint Textual and Phonetic Embedding.** [paper](https://arxiv.org/abs/1810.06729)
*Hairong Liu, Mingbo Ma, Liang Huang, hao xiong and Zhongjun He*
**Domain**: Robustness of NMT
31. **Self-Supervised Neural Machine Translation.** [paper](-)
*Dana Ruiter, Cristina España-Bonet and Josef van Genabith*
**Domain**: Low-resource
32. **Soft Contextual Data Augmentation for Neural Machine Translation.** [paper](https://arxiv.org/abs/1905.10523)
*Jinhua Zhu, Fei Gao, Lijun Wu, Yingce Xia, Tao QIN, Wengang Zhou, Xueqi Cheng and Tie-Yan Liu*
**Domain**: Low-resource
33. **Domain Adaptive Inference for Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.00408)
*Danielle Saunders, Felix Stahlberg, Adrià de Gispert and Bill Byrne*
**Domain**: Domain Adaptation
34. **Revisiting Low-Resource Neural Machine Translation: A Case Study.** [paper](https://arxiv.org/abs/1905.11901)
*Rico Sennrich and Biao Zhang*
**Domain**: Problem Analysis
35. **Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation.** [paper](https://arxiv.org/abs/1905.08212)
*Xinyi Wang and Graham Neubig*
**Domain**: Practical Problems in Machine Translation
36. **Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach.** [paper](-)
*Zonghan Yang, Yong Cheng, Yang Liu and Maosong Sun*
**Domain**: Practical Problems in Machine Translation
37. **Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation.** [paper](https://arxiv.org/abs/1906.05683)
*Nima Pourdamghani, Nada Aldarrab, Marjan Ghazvininejad, Kevin Knight and Jonathan May*
**Domain**: Low-resource
38. **Generating Diverse Translations with Sentence Codes.** [paper](-)
*Raphael Shu, Hideki Nakayama and Kyunghyun Cho*
**Domain**: Practical Problems in Machine Translation
39. **Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation.** [paper](https://arxiv.org/abs/1906.01199)
*Elizabeth Salesky, Matthias Sperber and Alan W Black*
**Domain**: Practical Problems in Machine Translation
40. **Training Neural Machine Translation To Apply Terminology Constraints.** [paper](https://arxiv.org/abs/1906.01105)
*Georgiana Dinu, Prashant Mathur, Marcello Federico and Yaser Al-Onaizan*
**Domain**: Practical Problems in Machine Translation
41. **Exploiting Sentential Context for Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.01268)
*Xing Wang, Zhaopeng Tu, Longyue Wang and Shuming Shi*
**Domain**: Context-aware NMT
42. **Depth Growing for Neural Machine Translation.** [paper](-)
*Lijun Wu, Yiren Wang, Yingce Xia, Fei Tian, Fei Gao, Tao QIN, Jianhuang Lai and Tie-Yan Liu*
**Domain**: Neural Network Architecture
43. **Effective Adversarial Regularization for Neural Machine Translation.** [paper](-)
*Motoki Sato, Jun Suzuki and Shun Kiyono*
**Domain**: Neural Network Architecture
44. **Evaluating Gender Bias in Machine Translation.** [paper](https://arxiv.org/abs/1906.00591)
*Gabriel Stanovsky, Noah A. Smith and Luke Zettlemoyer*
**Domain**: Problem Analysis
45. **Putting Evaluation in Context: Contextual Embeddings improve Machine Translation Evaluation.** [paper](-)
*Nitika Mathur, Timothy Baldwin and Trevor Cohn*
**Domain**: Context-aware NMT
46. **Sentence-Level Agreement for Neural Machine Translation.** [paper](-)
*Mingming Yang, Rui Wang, Kehai Chen, Masao Utiyama, eiichiro sumita, Min Zhang and Tiejun Zhao*
**Domain**: Problem Analysis
47. **Simple and Effective Paraphrastic Similarity from Parallel Translations.** [paper](-)
*John Wieting, Kevin Gimpel, Graham Neubig and Taylor Berg-Kirkpatrick*
**Domain**: Problem Analysis
48. **Bilingual Lexicon Induction through Unsupervised Machine Translation.** [paper](-)
*Mikel Artetxe, Gorka Labaka and Eneko Agirre*
**Domain**: Practical Problems in Machine Translation
49. **Better OOV Translation with Bilingual Terminology Mining.** [paper](-)
*Matthias Huck, Viktor Hangya and Alexander Fraser*
**Domain**: Practical Problems in Machine Translation
50. **Lattice-Based Transformer Encoder for Neural Machine Translation.** [paper](https://arxiv.org/abs/1906.01282)
*Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang and Kehai Chen*
**Domain**: Neural Network Architecture
51. **Simultaneous Translation with Flexible Policy via Restricted Imitation Learning.** [paper](https://arxiv.org/abs/1906.01135)
*Baigong Zheng, Renjie Zheng, Mingbo Ma and Liang Huang*
**Domain**: Practical Problems in Machine Translation
#### 2020
1. **Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation.** [paper](https://arxiv.org/abs/1909.09237)
*Arya D. McCarthy, Xian Li, Jiatao Gu, Ning Dong*
**Domain**: Neural Network Architecture
2. **Multiscale Collaborative Deep Models for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.40)
*Xiangpeng Wei, Heng Yu, Yue Hu, Yue Zhang, Rongxiang Weng and Weihua Luo*
**Domain**: Neural Network Architecture
3. **Hard-Coded Gaussian Attention for Neural Machine Translation.** [paper](https://arxiv.org/abs/2005.00742)
*Weiqiu You, Simeng Sun and Mohit Iyyer*
**Domain**: Neural Network Architecture
4. **Improving Neural Machine Translation with Soft Template Prediction.** [paper](https://www.aclweb.org/anthology/2020.acl-main.531/)
*Jian Yang, Shuming Ma, Dongdong Zhang, Zhoujun Li and Ming Zhou*
**Domain**: Neural Network Architecture
5. **Learning Source Phrase Representations for Neural Machine Translation.** [paper](https://arxiv.org/abs/2006.14405)
*Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu, Jingyi Zhang*
**Domain**: Neural Network Architecture
6. **A Reinforced Generation of Adversarial Examples for Neural Machine Translation.** [paper](https://arxiv.org/abs/1911.03677)
*Wei Zou, Shujian Huang, Jun Xie, Xinyu Dai, Jiajun Chen*
**Domain**: Data Augmentation
7. **Boosting Neural Machine Translation with Similar Translations.** [paper](https://www.aclweb.org/anthology/2020.acl-main.144/)
*Jitao XU, Josep Crego, Jean Senellart*
**Domain**: Data Augmentation
8. **Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.359)
*Xabier Soto, Dimitar Shterionov, Alberto Poncelas and Andy Way*
**Domain**: Data Augmentation
9. **AdvAug: Robust Adversarial Augmentation for Neural Machine Translation.** [paper](https://arxiv.org/abs/2006.11834)
*Yong Cheng, Lu Jiang, Wolfgang Macherey, Jacob Eisenstein*
**Domain**: Training
10. **Norm-Based Curriculum Learning for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.41)
*Xuebo Liu, Houtim Lai, Derek F. Wong and Lidia S. Chao*
**Domain**: Training
11. **Uncertainty-Aware Curriculum Learning for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.620)
*Yikai Zhou, Baosong Yang, Derek F. Wong, Yu Wan and Lidia S. Chao*
**Domain**: Training
12. **Balancing Training for Multilingual Neural Machine Translation.** [paper](https://arxiv.org/abs/2004.06748)
*Xinyi Wang, Yulia Tsvetkov and Graham Neubig*
**Domain**: Multilingual Translation
13. **Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation.** [paper](https://arxiv.org/abs/2004.11867)
*Biao Zhang, Philip Williams, Ivan Titov and Rico Sennrich*
**Domain**: Multilingual Translation
14. **Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation.** [paper](https://arxiv.org/abs/2004.10171)
*Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita and Tiejun Zhao*
**Domain**: Multilingual Translation
15. **Translationese as a Language in “Multilingual” NMT.** [paper](https://www.aclweb.org/anthology/2020.acl-main.691)
*Parker Riley, Isaac Caswell, Markus Freitag and David Grangier*
**Domain**: Multilingual Translation
16. **A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.273/)
*Yongjing Yin, Fandong Meng, Jinsong Su, Chulun Zhou, Zhengyuan Yang, Jie Zhou and Jiebo Luo*
**Domain**: Multimodal Translation
17. **Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting.** [paper](https://www.aclweb.org/anthology/2020.acl-main.731)
*Po-Yao Huang, Junjie Hu, Xiaojun Chang and Alexander Hauptmann*
**Domain**: Multimodal Translation
18. **Learning a Multi-Domain Curriculum for Neural Machine Translation.** [paper](https://arxiv.org/abs/1908.10940)
*Wei Wang, Ye Tian, Jiquan Ngiam, Yinfei Yang, Isaac Caswell, Zarana Parekh*
**Domain**: Multi-Domain
19. **Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing.** [paper](https://arxiv.org/abs/1911.02692)
*Haoming Jiang, Chen Liang, Chong Wang, Tuo Zhao*
**Domain**: Multi-Domain
20. **Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem.** [paper](https://www.aclweb.org/anthology/2020.acl-main.690)
*Danielle Saunders and Bill Byrne*
**Domain**: Domain Adaptation
21. **BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.** [paper](https://arxiv.org/abs/1910.13461)
*Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer*
**Domain**: Pre-Training
22. **Curriculum Pre-training for End-to-End Speech Translation.** [paper](https://arxiv.org/abs/2004.10093)
*Chengyi Wang, Yu Wu, Shujie Liu, Ming Zhou and Zhenglu Yang*
**Domain**: Pre-training
23. **Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences.** [paper](https://www.aclweb.org/anthology/2020.acl-main.143/)
*Xiangyu Duan, Baijun Ji, Hao Jia, Min Tan, Min Zhang, Boxing Chen, Weihua Luo, Yue Zhang*
**Domain**: Low-resource
24. **A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.320)
*Shuo Ren, Yu Wu, Shujie Liu, Ming Zhou and Shuai Ma*
**Domain**: Low-resource
25. **Document Translation vs. Query Translation for Cross-Lingual Information Retrieval in the Medical Domain.** [paper](https://www.aclweb.org/anthology/2020.acl-main.613/)
*Shadi Saleh and Pavel Pecina*
**Domain**: Cross-Lingual Information Retrieval
26. **Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation.** [paper](https://arxiv.org/abs/2005.06606)
*Xuanli He, Gholamreza Haffari, Mohammad Norouzi*
**Domain**: Subword Segmentation
27. **In Neural Machine Translation, What Does Transfer Learning Transfer?.** [paper](https://www.aclweb.org/anthology/2020.acl-main.688.pdf)
*Alham Fikri Aji, Nikolay Bogoychev, Kenneth Heafield and Rico Sennrich*
**Domain**: Problem Analysis
28. **Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.36/)
*Junliang Guo, Linli Xu and Enhong Chen*
**Domain**: Non-Autoregressive Translation
29. **Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation.** [paper](https://arxiv.org/abs/2006.05165)
*Qiu Ran, Yankai Lin, Peng Li, Jie Zhou*
**Domain**: Non-Autoregressive Translation
30. **Multi-Hypothesis Machine Translation Evaluation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.113)
*Marina Fomicheva, Lucia Specia and Francisco Guzmán*
**Domain**: Evaluation
31. **On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.151)
*Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West and Steffen Eger*
**Domain**: Evaluation
32. **On The Evaluation of Machine Translation SystemsTrained With Back-Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.253)
*Sergey Edunov, Myle Ott, Marc’Aurelio Ranzato and Michael Auli*
**Domain**: Evaluation
33. **Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics.** [paper](https://www.aclweb.org/anthology/2020.acl-main.448)
*Nitika Mathur, Timothy Baldwin and Trevor Cohn*
**Domain**: Evaluation
34. **Evaluating Explanation Methods for Neural Machine Translation.** [paper](https://arxiv.org/abs/2005.01672)
*Jierui Li, Lemao Liu, Huayang Li, Guanlin Li, Guoping Huang and Shuming Shi*
**Domain**: Evaluation
35. **On the Inference Calibration of Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.278)
*Shuo Wang, Zhaopeng Tu, Shuming Shi and Yang Liu*
**Domain**: Problem Analysis
36. **Regularized Context Gates on Transformer for Machine Translation.** [paper](https://arxiv.org/abs/1908.11020)
*Xintong Li, Lemao Liu, Rui Wang, Guoping Huang and Max Meng*
**Domain**: Neural Network Architecture
37. **Character-Level Translation with Self-attention.** [paper](https://www.aclweb.org/anthology/2020.acl-main.145)
*Yingqiang Gao, Nikola I. Nikolov, Yuhuang Hu and Richard H.R. Hahnloser*
**Domain**: Neural Network Architecture
38. **Variational Neural Machine Translation with Normalizing Flows.** [paper](https://www.aclweb.org/anthology/2020.acl-main.694/)
*Variational Neural Machine Translation with Normalizing Flows*
**Domain**: Neural Network Architecture
39. **Enhancing Machine Translation with Dependency-Aware Self-Attention.** [paper](https://www.aclweb.org/anthology/2020.acl-main.147)
*Emanuele Bugliarello and Naoaki Okazaki*
**Domain**: Neural Network Architecture
40. **Content Word Aware Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.34)
*Kehai Chen, Rui Wang, Masao Utiyama and Eiichiro Sumita*
**Domain**: Training
41. **Using Context in Neural Machine Translation Training Objectives.** [paper](https://www.aclweb.org/anthology/2020.acl-main.693.pdf)
*Danielle Saunders, Felix Stahlberg and Bill Byrne*
**Domain**: Training
42. **A Simple and Effective Unified Encoder for Document-Level Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.321)
*Shuming Ma, Dongdong Zhang and Ming Zhou*
**Domain**: Context-Aware Translation
43. **Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns.** [paper](https://www.aclweb.org/anthology/2020.acl-main.530)
*KayYen Wong, Sameen Maruf and Gholamreza Haffari*
**Domain**: Context-Aware Translation
44. **Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.322.pdf)
*Bei Li, Hui Liu, Ziyang Wang, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu and Changliang Li*
**Domain**: Context-Aware Translation
45. **ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.251)
*Lifu Tu, Richard Yuanzhe Pang, Sam Wiseman and Kevin Gimpel*
**Domain**: Non-Autoregressive Translation
46. **Lexically Constrained Neural Machine Translation with Levenshtein Transformer.** [paper](https://arxiv.org/abs/2004.12681)
*Raymond Hendy Susanto, Shamil Chollampatt and Liling Tan*
**Domain**: Non-Autoregressive Translation
47. **Improving Non-autoregressive Neural Machine Translation with Monolingual Data.** [paper](https://arxiv.org/abs/2005.00932)
*Jiawei Zhou and Phillip Keung*
**Domain**: Non-autoregressive Translation
48. **Evaluating Robustness to Input Perturbations for Neural Machine Translation.** [paper](https://arxiv.org/abs/2005.00580)
*Xing Niu, Prashant Mathur, Georgiana Dinu and Yaser Al-Onaizan*
**Domain**: Evaluation
49. **It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information.** [paper](https://arxiv.org/abs/2005.02354)
*Emanuele Bugliarello, Sabrina J. Mielke, Antonios Anastasopoulos, Ryan Cotterell and Naoaki Okazaki*
**Domain**: Evaluation
50. **Automatic Machine Translation Evaluation using Source Language Inputs and Cross-lingual Language Model.** [paper](https://www.aclweb.org/anthology/2020.acl-main.327)
*Kosuke Takahashi, Katsuhito Sudoh and Satoshi Nakamura*
**Domain**: Evaluation
51. **Language-aware Interlingua for Multilingual Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.150/)
*Changfeng Zhu, Heng Yu, Shanbo Cheng and Weihua Luo*
**Domain**: Multilingual Translation
52. **Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation.** [paper](https://arxiv.org/abs/2005.04816)
*Aditya Siddhant, Ankur Bapna, Yuan Cao, Orhan Firat, Mia Chen, Sneha Kudugunta, Naveen Arivazhagan and Yonghui Wu*
**Domain**: Multilingual Translation
53. **Multimodal Transformer for Multimodal Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.400/)
*Shaowei Yao and Xiaojun Wan*
**Domain**: Multimodal Translation
54. **Opportunistic Decoding with Timely Correction for Simultaneous Translation.** [paper](https://arxiv.org/abs/2005.00675)
*Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu and Liang Huang*
**Domain**: Simultaneous Translation
55. **Simultaneous Translation Policies: From Fixed to Adaptive.** [paper](https://arxiv.org/abs/2004.13169)
*Baigong Zheng, Kaibo Liu, Renjie Zheng, Mingbo Ma, Hairong Liu and Liang Huang*
**Domain**: Simultaneous Translation
56. **Tagged Back-translation Revisited: Why Does It Really Work?.** [paper](https://www.aclweb.org/anthology/2020.acl-main.532)
*Benjamin Marie, Raphael Rubino and Atsushi Fujita*
**Domain**: Data Augmentation
57. **Modeling Word Formation in English–German Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.389)
*Marion Weller-Di Marco and Alexander Fraser*
**Domain**: Practical Problems in Machine Translation
58. **``You Sound Just Like Your Father’’ Commercial Machine Translation Systems Include Stylistic Biases.** [paper](https://www.aclweb.org/anthology/2020.acl-main.154/)
*Dirk Hovy, Federico Bianchi and Tommaso Fornaciari*
**Domain**: Practical Problems in Machine Translation
59. **On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation.** [paper](https://arxiv.org/abs/2005.03642)
*Chaojun Wang and Rico Sennrich*
**Domain**: Practical Problems in Machine Translation
60. **A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.320)
*Shuo Ren, Yu Wu, Shujie Liu, Ming Zhou and Shuai Ma*
**Domain**: Low-resource
### EMNLP
#### 2018
1. **Meta-Learning for Low-Resource Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1398)
*Jiatao Gu, Yong Wang, Yun Chen, Kyunghyun Cho and Victor O.K. Li*
**Domain**: Low-resource
2. **Unsupervised Statistical Machine Translation.** [paper](http://aclweb.org/anthology/D18-1399)
*Mikel Artetxe, Gorka Labaka and Eneko Agirre*
**Domain**: Low-resource
3. **Phrase-Based & Neural Unsupervised Machine Translation.** [paper](http://aclweb.org/anthology/D18-1549)
*Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc’Aurelio Ranzato*
**Domain**: Low-resource
4. **Contextual Parameter Generation for Universal Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1039)
*Emmanouil Antonios Platanios, Mrinmaya Sachan, Graham Neubig, Tom M. Mitchell*
**Domain**: Domain Adaptation
5. **Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination.** [paper](http://aclweb.org/anthology/D18-1041)
*Jiali Zeng, Jinsong Su, Huating Wen, Yang Liu, Jun Xie, Yongjing Yin and Jianqiang Zhao*
**Domain**: Domain Adaptation
6. **A Study of Reinforcement Learning for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1397)
*Lijun Wu, Fei Tian, Tao Qin, Jianhuang Lai and Tie-Yan Liu*
**Domain**: Training
7. **A Visual Attention Grounding Neural Model for Multimodal Machine Translation.** [paper](http://aclweb.org/anthology/D18-1400)
*Mingyang Zhou, Runxiang Cheng, Yong Jae Lee, Zhou Yu*
**Domain**: Multimodal Translation
8. **Adaptive Multi-pass Decoder for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1048)
*Xinwei Geng and Xiaocheng Feng and Bing Qin and Ting Liu*
**Domain**: Neural Network Architecture
9. **Exploiting Deep Representations for Neural Machine Translation.** [paper](https://aclweb.org/anthology/D18-1457)
*Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Shuming Shi and Tong Zhang*
**Domain**: Neural Network Architecture
10. **Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks.** [paper](http://aclweb.org/anthology/D18-1459)
*Biao Zhang, Deyi Xiong, Jinsong Su, Qian Lin and Huiji Zhang*
**Domain**: Neural Network Architecture
11. **Modeling Localness for Self-Attention Networks.** [paper](http://aclweb.org/anthology/D18-1475)
*Baosong Yang, Zhaopeng Tu, Derek F. Wong, Fandong Meng, Lidia S. Chao and Tong Zhang*
**Domain**: Neural Network Architecture
12. **Addressing Troublesome Words in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1036)
*Yang Zhao, Jiajun Zhang, Zhongjun He,Chengqing Zong and Hua Wu*
**Domain**: Neural Network Architecture
13. **Revisiting Character-Based Neural Machine Translation with Capacity and Compression.** [paper](http://aclweb.org/anthology/D18-1461)
*Colin Cherry, George Foster, Ankur Bapna, Orhan Firat and Wolfgang Macherey*
**Domain**: Neural Network Architecture
14. **Speeding Up Neural Machine Translation Decoding by Cube Pruning.** [paper](http://aclweb.org/anthology/D18-1460)
*Wen Zhang, Liang Huang, Yang Feng, Lei Shen and Qun Liu*
**Domain**: Decoding
15. **Semi-Autoregressive Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1044)
*Chunqi Wang, Ji Zhang and Haiqing Chen*
**Domain**: Decoding
16. **Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing.** [paper](http://aclweb.org/anthology/D18-1037)
*Jetic Gu, Hassan S. Shavarani and Anoop Sarkar*
**Domain**: External Knowledge
17. **Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1040)
*Marzieh Fadaee and Christof Monz*
**Domain**: Back Translation
18. **Understanding Back-Translation at Scale.** [paper](http://aclweb.org/anthology/D18-1045)
*Sergey Edunov, Myle Ott, Michael Auli and David Grangier*
**Domain**: Back Translation
19. **MTNT: A Testbed for Machine Translation of Noisy Text.** [paper](http://aclweb.org/anthology/D18-1050)
*Paul Michel and Graham Neubig*
**Domain**: Corpus
20. **Improving the Transformer Translation Model with Document-Level Context.** [paper](http://aclweb.org/anthology/D18-1049)
*Jiacheng Zhang, Huanbo Luan,Maosong Sun, FeiFei Zhai, Jingfang Xu, Min Zhang and Yang Liu*
**Domain**: Document-Level NMT
21. **Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures.** [paper](http://aclweb.org/anthology/D18-1458)
*Gongbo Tang, Mathias Muller, Annette Rios and Rico Sennrich*
**Domain**: Analysis
22. **Compact Personalized Models for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1104)
*Joern Wuebker, Patrick Simianer and John DeNero*
**Domain**: Domain Adaptation
23. **Rapid Adaptation of Neural Machine Translation to New Languages.** [paper](http://aclweb.org/anthology/D18-1103)
*Graham Neubig and Junjie Hu*
**Domain**: Domain Adaptation
24. **The Lazy Encoder A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1313)
*Arianna Bisazza and Clara Tump*
**Domain**: External Knowledge
25. **Context and Copying in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1339)
*Rebecca Knowles and Philipp Koehn*
**Domain**: Neural Network Architecture
26. **Adversarial Evaluation of Multimodal Machine Translation.** [paper](http://aclweb.org/anthology/D18-1329)
*Desmond Elliott*
**Domain**: Multimodal Translation
27. **Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1331)
*Junyang Lin, Xu Sun, Xuancheng Ren, Muyu Li, Qi Su*
**Domain**: Neural Network Architecture
28. **Encoding Gated Translation Memory into Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1340)
*Qian Cao and Deyi Xiong*
**Domain**: Neural Network Architecture
29. **Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1335)
*Parnia Bahar, Christopher Brix and Hermann Ney*
**Domain**: Neural Network Architecture
30. **Training Deeper Neural Machine Translation Models with Transparent Attention.** [paper](https://aclweb.org/anthology/D18-1338)
*Ankur Bapna, Mia Xu Chen, Orhan Firat, Yuan Cao and Yonghui Wu*
**Domain**: Neural Network Architecture
31. **Learning When to Concentrate or Divert Attention:Self-Adaptive Attention Temperature for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1331)
*Junyang Lin, Xu Sun, Xuancheng Ren, Muyu Li and Qi Su*
**Domain**: Neural Network Architecture
32. **Multi-Head Attention with Disagreement Regularization.** [paper](http://aclweb.org/anthology/D18-1317)
*Jian Li, Zhaopeng Tu, Baosong Yang, Michael R. Lyu and Tong Zhang*
**Domain**: Neural Network Architecture
33. **Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1335)
*Parnia Bahar, Christopher Brix and Hermann Ney*
**Domain**: Neural Network Architecture
34. **Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1332)
*Nikolay Bogoychev, Marcin Junczys-Dowmunt, Kenneth Heafield and Alham Fikri Aji*
**Domain**: Training
35. **Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D18-1510)
*Chenze Shao, Yang Feng, Xilin Chen*
**Domain**: Training
36. **Exploring Recombination for Efficient Decoding of Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1511)
*Zhisong Zhang, Rui Wang,Masao Utiyama, Eiichiro Sumita and Hai Zhao*
**Domain**: Decoding
37. **Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1342)
*Yilin Yang, Liang Huang and Mingbo Ma*
**Domain**: Decoding
38. **End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification.** [paper](http://aclweb.org/anthology/D18-1336)
*Jindrich Libovicky and Jindrich Helcl*
**Domain**: Decoding
39. **Multi-Source Syntactic Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1327)
*Anna Currey and Kenneth Heafield*
**Domain**: External Knowledge
40. **A Tree-based Decoder for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1509)
*Xinyi Wang, Hieu Pham, Pengcheng Yin and Graham Neubig*
**Domain**: External Knowledge
41. **SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1100)
*Xinyi Wang, Hieu Pham, Zihang Dai and Graham Neubig*
**Domain**: Data Augmentation
42. **Fixing Translation Divergences in Parallel Corpora for Neural MT.** [paper](http://aclweb.org/anthology/D18-1328)
*MinhQuang Pham, Josep Crego, Jean Senellart and Franc¸ois Yvon*
**Domain**: Data Processing
43. **Getting Gender Right in Neural Machine Translation.** [paper](http://aclweb.org/anthology/D18-1334)
*Eva Vanmassenhove, Christian Hardmeier and Andy Way*
**Domain**: Corpus
44. **Document-Level Neural Machine Translation with Hierarchical Attention Networks.** [paper](http://aclweb.org/anthology/D18-1325)
*Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas and James Henderson*
**Domain**: Document-Level NMT
45. **Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation.** [paper](https://www.aclweb.org/anthology/D18-1512)
*Samuel Laubli, Rico Sennrich, Martin Volk*
**Domain**: Document-Level NMT
46. **The Lazy Encoder: A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D18-1313)
*Arianna Bisazza, Clara Tump*
**Domain**: Analysis
47. **Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter.** [paper](https://www.aclweb.org/anthology/D18-1396)
*Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu*
**Domain**: Analysis
48. **Automatic Post-Editing of Machine Translation: A Neural Programmer-Interpreter Approach.** [paper](https://www.aclweb.org/anthology/D18-1341)
*Thuy-Trang Vu, Gholamreza Haffari*
**Domain**: Post-Editting
#### 2019
1. **Explicit Cross-lingual Pre-training for Unsupervised Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1071.pdf)
*Ren Shuo, Wu Yu, Liu Shujie, Zhou Ming and Ma, Shuai*
**Domain**: Unsupervised
2. **Latent Part-of-Speech Sequences for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1072.pdf)
*Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian*
**Domain**: External Knowledge
3. **Towards Linear Time Neural Machine Translation with Capsule Networks.** [paper](https://www.aclweb.org/anthology/D19-1074.pdf)
*Mingxuan Wang*
**Domain**: Neural Network Architecture
4. **Iterative Dual Domain Adaptation for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1078.pdf)
*Jiali Zeng, Yang Liu, jinsong su, yubing Ge, Yaojie Lu, Yongjing Yin, jiebo luo*
**Domain**: Domain Adaptation
5. **Multi-agent Learning for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1079.pdf)
*tianchi bi, hao xiong, Zhongjun He, Hua Wu, Haifeng Wang*
**Domain**: Ensemble Training
6. **Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages.** [paper](https://www.aclweb.org/anthology/D19-1080.pdf)
*Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney*
**Domain**: Pre-training
7. **Context-Aware Monolingual Repair for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1081.pdf)
*Elena Voita, Rico Sennrich, Ivan Titov*
**Domain**: Document Level
8. **Multi-Granularity Self-Attention for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1082.pdf)
*Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu*
**Domain**: Neural Network Architecture
9. **Dynamic Past and Future for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1086.pdf)
*Zaixiang Zheng, Shujian Huang, Zhaopeng Tu, XIN-YU DAI, Jiajun CHEN*
**Domain**: Coverage
10. **Towards Understanding Neural Machine Translation with Word Importance.** [paper](https://www.aclweb.org/anthology/D19-1088.pdf)
*Shilin He, Zhaopeng Tu, Xing Wang, Longyue Wang, Michael Lyu, Shuming Shi*
**Domain**: Interpretability
11. **Multilingual Neural Machine Translation with Language Clustering.** [paper](https://www.aclweb.org/anthology/D19-1089.pdf)
*Xu Tan, Jiale Chen, Di He, Yingce Xia, Tao QIN, Tie-Yan Liu*
**Domain**: Multilingual
12. **Simple, Scalable Adaptation for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1165.pdf)
*Ankur Bapna, Orhan Firat*
**Domain**: Fine Tuning
13. **Controlling Text Complexity in Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1166.pdf)
*Sweta Agrawal, Marine Carpuat*
**Domain**: Text Complexity
14. **Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1168.pdf)
*Xin Tan, Longyin Zhang, Deyi Xiong, Guodong Zhou*
**Domain**: Document Level
15. **Evaluating Pronominal Anaphora in Machine Translation: An Evaluation Measure and a Test Suite.** [paper](https://www.aclweb.org/anthology/D19-1294.pdf)
*Prathyusha Jwalapuram, Shafiq Joty, Irina Temnikova, Preslav Nakov*
**Domain**: Evaluation Measure
16. **Exploiting Monolingual Data at Scale for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1430.pdf)
*Lijun Wu, Yiren Wang, Yingce Xia, Tao QIN, Jianhuang Lai, Tie-Yan Liu*
**Domain**: Data Augmentation
17. **Machine Translation With Weakly Paired Documents.** [paper](https://www.aclweb.org/anthology/D19-1446.pdf)
*Lijun Wu, Jinhua Zhu, Di He, Fei Gao, Tao QIN, Jianhuang Lai, Tie-Yan Liu*
**Domain**: Data Augmentation
18. **Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel.** [paper](https://www.aclweb.org/anthology/D19-1443.pdf)
*Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov*
**Domain**: Neural Network Architecture
19. **Attention is not not Explanation.** [paper](https://www.aclweb.org/anthology/D19-1002.pdf)
*Sarah Wiegreffe, Yuval Pinter*
**Domain**: Interpretability
20. **The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English.** [paper](https://www.aclweb.org/anthology/D19-1632.pdf)
*Francisco Guzmán, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, Marc’Aurelio Ranzato*
**Domain**: corpus
21. **The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives.** [paper](https://www.aclweb.org/anthology/D19-1448.pdf)
*Elena Voita, Rico Sennrich, Ivan Titov*
**Domain**: Analysis
22. **Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention.** [paper](https://www.aclweb.org/anthology/D19-1083.pdf)
*Biao Zhang, Ivan Titov, Rico Sennrich*
**Domain**: Neural Network Architecture/Deep model
23. **Tree Transformer: Integrating Tree Structures into Self-Attention.** [paper](https://www.aclweb.org/anthology/D19-1098.pdf)
*Yaushian Wang, Hung-Yi Lee, Yun-Nung Chen*
**Domain**: Neural Network Architecture
24. **Adaptively Sparse Transformers.** [paper](https://www.aclweb.org/anthology/D19-1223.pdf)
*Gonçalo M. Correia, Vlad Niculae, André F. T. Martins*
**Domain**: Neural Network Architecture
25. **Jointly Learning to Align and Translate with Transformer Models.** [paper](https://www.aclweb.org/anthology/D19-1453.pdf)
*Sarthak Garg, Stephan Peitz, Udhyakumar Nallasamy, Matthias Paulik*
**Domain**: Neural Network Architecture
26. **LXMERT: Learning Cross-Modality Encoder Representations from Transformers.** [paper](https://www.aclweb.org/anthology/D19-1514.pdf)
*Hao Tan, Mohit Bansal*
**Domain**: Pre-training
27. **Encoders Help You Disambiguate Word Senses in Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1149.pdf)
*Gongbo Tang, Rico Sennrich, Joakim Nivre*
**Domain**: Interpretability
28. **Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings.** [paper](https://www.aclweb.org/anthology/D19-1147.pdf)
*Zi-Yi Dou, Junjie Hu, Antonios Anastasopoulos, Graham Neubig*
**Domain**: Domain Adaptation
29. **Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1146.pdf)
*Raj Dabre, Atsushi Fujita, Chenhui Chu*
**Domain**: Multilingual / Low Resource
30. **Handling Syntactic Divergence in Low-resource Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1143.pdf)
*Chunting Zhou, Xuezhe Ma, Junjie Hu, Graham Neubig*
**Domain**: Low Resource
31. **HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1142.pdf)
*Brian Thompson, Rebecca Knowles, Xuan Zhang, Huda Khayrallah, Kevin Duh, Philipp Koehn*
**Domain**: External Knowledge
32. **Machine Translation for Machines: the Sentiment Classification Use Case.** [paper](https://www.aclweb.org/anthology/D19-1140.pdf)
*amirhossein tebbifakhr, Luisa Bentivogli, Matteo Negri, Marco Turchi*
**Domain**: Training
33. **Recurrent Positional Embedding for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1139.pdf)
*Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita*
**Domain**: Neural Network Architecture
34. **Self-Attention with Structural Position Representations.** [paper](https://www.aclweb.org/anthology/D19-1145.pdf)
*Xing Wang, Zhaopeng Tu, Longyue Wang, Shuming Shi*
**Domain**: Neural Network Architecture
35. **Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons.** [paper](https://www.aclweb.org/anthology/D19-1135.pdf)
*Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu*
**Domain**: Neural Network Architecture
36. **Hint-Based Training for Non-Autoregressive Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1573.pdf)
*Zhuohan Li, Zi Lin, Di He, Fei Tian, Tao QIN, Liwei WANG, Tie-Yan Liu*
**Domain**: Non-AutoRegressive Translation
37. **Simple and Effective Noisy Channel Modeling for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/D19-1571.pdf)
*Kyra Yee, Yann Dauphin, Michael Auli*
**Domain**: Neural Network Architecture
38. **Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization.** [paper](https://www.aclweb.org/anthology/D19-1570.pdf)
*Guanlin Li, Lemao Liu, Guoping Huang, Conghui Zhu, Tiejun Zhao*
**Domain**: Data Augmentation
### NAACL
#### 2018
1. **Universal Neural Machine Translation for Extremely Low Resource Languages.** [paper](http://aclweb.org/anthology/N18-1032)
*Jiatao Gu, Hany Hassan, Jacob Devlin and Victor O.K. Li*
**Domain**: Low-resource
2. **Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach.** [paper](http://aclweb.org/anthology/N18-1123)
*Poorya Zaremoodi and Gholamreza Haffari*
**Domain**: Low-resource
3. **Evaluating Discourse Phenomena in Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1118)
*Rachel Bawden, Rico Sennrich, Alexandra Birch and Barry Haddow*
**Domain**: Context-aware NMT
4. **On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference.** [paper](http://aclweb.org/anthology/N18-2082)
*Adam Poliak, Yonatan Belinkov, James Glass and Benjamin Van Durme*
**Domain**: Problem Analysis
5. **Improving Lexical Choice in Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1031)
*Toan Q. Nguyen and David Chiang*
**Domain**: Neural Network Architecture
6. **Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention.** [paper](http://aclweb.org/anthology/N18-1116)
*Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, Jiajun Chen*
**Domain**: Neural Network Architecture
7. **Dense Information Flow for Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1117)
*Yanyao Shen, Xu Tan, Di He, Tao Qin, and Tie-Yan Liu*
**Domain**: Neural Network Architecture
8. **Self-Attentive Residual Decoder for Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1124)
*Lesly Miculicich Werlen, Nikolaos Pappas, Dhananjay Ram and Andrei Popescu-Belis*
**Domain**: Neural Network Architecture
9. **Target Foresight based Attention for Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1125)
*Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng*
**Domain**: Neural Network Architecture
10. **Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets.** [paper](http://aclweb.org/anthology/N18-1122)
*Zhen Yang, Wei Chen, Feng Wang and Bo Xu*
**Domain**: Training
11. **Can Neural Machine Translation be Improved with User Feedback?.** [paper](http://aclweb.org/anthology/N18-3012)
*Julia Kreutzer, Shahram Khadivi3, Evgeny Matusov and Stefan Riezler*
**Domain**: Training
12. **Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1119)
*Matt Post and David Vilar*
**Domain**: Decoding
13. **Guiding Neural Machine Translation with Retrieved Translation Pieces.** [paper](http://aclweb.org/anthology/N18-1120)
*Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig and Satoshi Nakamura*
**Domain**: Decoding
14. **Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1006)
*Peyman Passban, Qun Liu and Andy Way*
**Domain**: External Knowledge
15. **Handling Homographs in Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-1121)
*Frederick Liu, Han Lu and Graham Neubig*
**Domain**: External Knowledge
16. **Neural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced from Comparable Corpora.** [paper](http://aclweb.org/anthology/N18-4016)
*Sree Harsha Ramesh and Krishna Prasad Sankaranarayanan*
**Domain**: Data Processing
17. **Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models.** [paper](http://aclweb.org/anthology/N18-2080)
*David Vilar*
**Domain**: Domain Adaptation
18. **Neural Machine Translation Decoding with Terminology Constraints.** [paper](http://aclweb.org/anthology/N18-2081)
*Eva Hasler, Adria de Gispert, Gonzalo Iglesias and Bill Byrne*
**Domain**: Decoding
19. **Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-2079)
*JFahim Dalvi, Nadir Durrani, Hassan Sajjad and Stephan Vogel*
**Domain**: Decoding
20. **Pieces of Eight: 8-bit Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-3014)
*Jerry Quinn and Miguel Ballesteros*
**Domain**: Practical Problems in Machine Translation
21. **Japanese Predicate Conjugation for Neural Machine Translation.** [paper](http://aclweb.org/anthology/N18-4014)
*Michiki Kurosawa, Yukio Matsumura, Hayahide Yamagishi and Mamoru Komachi*
**Domain**: External Knowledge
22. **Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks.** [paper](http://aclweb.org/anthology/N18-2078)
*Diego Marcheggiani, Joost Bastings and Ivan Titov*
**Domain**: External Knowledge
23. **Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation.** [paper](http://aclweb.org/anthology/N18-2077)
*Marianna Apidianaki, Guillaume Wisniewski, Anne Cocos and Chris Callison-Burch*
**Domain**: Problem Analysis
24. **Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations.** [paper](http://aclweb.org/anthology/N18-4015)
*Hiroki Shimanaka, Tomoyuki Kajiwara and Mamoru Komachi*
**Domain**: Problem Analysis
25. **When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?.** [paper](http://aclweb.org/anthology/N18-2084)
*Ye Qi, Devendra Singh Sachan, Matthieu Felix, Sarguna Janani Padmanabhan and Graham Neubig*
**Domain**: Problem Analysis
26. **Self-Attention with Relative Position Representations.** [paper](https://aclweb.org/anthology/papers/N/N18/N18-2074/)
*Peter Shaw, Jakob Uszkoreit, Ashish Vaswani*
**Domain**: Neural Network Architecture
#### 2019
1. **Consistency by Agreement in Zero-Shot Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1121.pdf)
*Maruan Al Shedivat, Ankur Parikh*
**Domain**: Low Resource
2. **Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1120.pdf)
*Jiawei Wu, Xin Wang, William Yang Wang*
**Domain**: Low Resource
3. **Comparing Pipelined and Integrated Approaches to Dialectal Arabic Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/W19-1424.pdf)
*Pamela Shapiro, Kevin Duh*
**Domain**: Problem Analysis
4. **Neural Machine Translation between Myanmar (Burmese) and Rakhine (Arakanese).** [paper](https://www.aclweb.org/anthology/W19-1408.pdf)
*Thazin Myint Oo, Ye Kyaw Thu, Khin Mar Soe*
**Domain**: Problem Analysis
5. **Measuring Immediate Adaptation Performance for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1206.pdf)
*Patrick Simianer, Joern Wuebker, John DeNero*
**Domain**: Domain Adaption
6. **Non-Parametric Adaptation for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1191.pdf)
*Ankur Bapna, Orhan Firat*
**Domain**: Domain Adaption
7. **Curriculum Learning for Domain Adaptation in Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1189.pdf)
*Xuan Zhang, Pamela Shapiro, Gaurav Kumar, Paul McNamee, Marine Carpuat, Kevin Duh*
**Domain**: Domain Adaption
8. **Massively Multilingual Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1388.pdf)
*Roee Aharoni, Melvin Johnson, Orhan Firat*
**Domain**: Multilingual
9. **Probing the Need for Visual Context in Multimodal Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1422.pdf)
*Ozan Caglayan, Pranava Madhyastha, Lucia Specia, Loïc Barrault*
**Domain**: Multimodal NMT
10. **Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations.** [paper](https://www.aclweb.org/anthology/N19-1118.pdf)
*Meishan Zhang, Zhenghua Li, Guohong Fu, Min Zhang*
**Domain**: Syntax Aware
11. **Online Distilling from Checkpoints for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1192.pdf)
*Hao-Ran Wei, Shujian Huang, Ran Wang, Xin-yu Dai, Jiajun Chen*
**Domain**: Training
12. **Reinforcement Learning based Curriculum Optimization for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1208.pdf)
*Gaurav Kumar, George Foster, Colin Cherry, Maxim Krikun*
**Domain**: Training
13. **Competence-based Curriculum Learning for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1119.pdf)
*Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, Tom Mitchell*
**Domain**: Training, Curriculum Learning
14. **Understanding and Improving Hidden Representations for Neural MachineTranslation.** [paper](https://www.aclweb.org/anthology/N19-1046.pdf)
*Guanlin Li, Lemao Liu, Xintong Li, Conghui Zhu, Tiejun Zhao, Shuming Shi*
**Domain**: Training, Problem Analysis
15. **Unsupervised Extraction of Partial Translations for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1384.pdf)
*Benjamin Marie, Atsushi Fujita*
**Domain**: Data Augmentation
16. **Selective Attention for Context-aware Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1313.pdf)
*Sameen Maruf, André F. T. Martins, Gholamreza Haffari*
**Domain**: Contex aware
17. **Neural Machine Translation of Text from Non-Native Speakers.** [paper](https://www.aclweb.org/anthology/N19-1311.pdf)
*Antonios Anastasopoulos, Alison Lui, Toan Q. Nguyen, David Chiang*
**Domain**: Robustness of NMT
18. **Star-Transformer.** [paper](https://www.aclweb.org/anthology/N19-1133.pdf)
*Qipeng Guo, Xipeng Qiu, Pengfei Liu, Yunfan Shao, Xiangyang Xue, Zheng Zhang*
**Domain**: Neural Network Architecture
19. **Modeling Recurrence for Transformer.** [paper]()
*Jie Hao, Xing Wang, Baosong Yang, Longyue Wang, Jinfeng Zhang, Zhaopeng Tu*
**Domain**: Neural Network Architecture
20. **Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1209.pdf)
*Brian Thompson, Jeremy Gwinnup, Huda Khayrallah, Kevin Duh, Philipp Koehn*
**Domain**: Domain Adaption
21. **Addressing word-order Divergence in Multilingual Neural Machine Translation for extremely Low Resource Languages.** [paper](https://www.aclweb.org/anthology/N19-1387.pdf)
*Rudra Murthy, Anoop Kunchukuttan, Pushpak Bhattacharyya*
**Domain**: Transfer Learning, Low Resource
22. **Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1043.pdf)
*Xing Niu, Weijia Xu, Marine Carpuat*
**Domain**: Low Resource
23. **Convolutional Self-attention Networks.** [paper](https://www.aclweb.org/anthology/N19-1407)
*Baosong Yang, Longyue Wang, Derek F. Wong, Lidia S. Chao, Zhaopeng Tu*
**Domain**: Neural Network Architecture
24. **Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1207.pdf)
*Weijia Xu, Xing Niu, Marine Carpuat*
**Domain**: Training
25. **ReWE: Regressing Word Embeddings for Regularization of Neural Machine Translation Systems.** [paper](https://www.aclweb.org/anthology/N19-1041.pdf>)
*Inigo Jauregi Unanue, Ehsan Zare Borzeshi, Nazanin Esmaili, Massimo Piccardi*
**Domain**: Training
26. **Lost in Machine Translation: A Method to Reduce Meaning Loss.** [paper](https://www.aclweb.org/anthology/N19-1042.pdf)
*Reuben Cohn-Gordon, Noah Goodman*
**Domain**: Training
27. **Improving Neural Machine Translation with Neural Syntactic Distance.** [paper](https://www.aclweb.org/anthology/N19-1205.pdf)
*Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao*
**Domain**: Syntax Aware
28. **Improving Robustness of Machine Translation with Synthetic Noise.** [paper](https://www.aclweb.org/anthology/N19-1190.pdf)
*Vaibhav Vaibhav, Sumeet Singh, Craig Stewart, Graham Neubig*
**Domain**: Robustness
29. **Learning to Stop in Structured Prediction for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/N19-1187.pdf)
*Mingbo Ma, Renjie Zheng, Liang Huang*
**Domain**: Decoding
30. **Multimodal Machine Translation with Embedding Prediction.** [paper](https://www.aclweb.org/anthology/N19-3012.pdf)
*Tosho Hirasawa, Hayahide Yamagishi, Yukio Matsumura, Mamoru Komachi*
**Domain**: Multimodal
### AAAI
#### 2020
1. **Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation.** [paper](https://arxiv.org/abs/1911.09320)
*Chenze Shao, Jinchao Zhang, Yang Feng, Fandong Meng and Jie Zhou*
**Domain**: Training, Non-Autoregressive NMT
2. **Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior.** [paper](https://arxiv.org/abs/1908.07181)
*Raphael Shu, Jason Lee, Hideki Nakayama, and Kyunghyun Cho*
**Domain**: Non-Autoregressive NMT
3. **Neural Machine Translation with Byte-Level Subwords.** [paper](https://arxiv.org/abs/1909.03341)
*Changhan Wang, Kyunghyun Cho and Jiatao Gu*
**Domain**: Data Processing
4. **Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation.** [paper](https://arxiv.org/abs/1911.08717)
*Junliang Guo, Xu Tan, Linli Xu, Tao Qin, Enhong Chen, Tie-Yan Liu*
**Domain**: Curriculum Learning, Non-Autoregressive NMT
5. **Reinforced Curriculum Learning on Pre-trained Neural Machine Translation Models.** [paper](-)
*Mingjun Zhao, Haijiang Wu, Di Niu, Xiaoli Wang*
**Domain**: Curriculum Learning
6. **Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling.** [paper](https://arxiv.org/abs/1912.05134)
*Yu Wan, Baosong Yang, Derek F. Wong, Lidia S. Chao, Haihua Du, Ben C.H. Ao*
**Domain**: Unsupervised
7. **Transductive Ensemble Learning for Neural Machine Translation.** [paper](-)
*Yiren Wang, Lijun Wu, Yingce Xia, Tao Qin, ChengXiang Zhai, Tie-Yan Liu*
**Domain**: Ensemble Learning
8. **Improving Context-Aware Neural Machine Translation Using Self-Attentive Sentence Embedding.** [paper](-)
*Hyeongu Yun, Yongkeun Hwang, Kyomin Jung*
**Domain**: Context-Aware NMT
9. **Controlling Neural Machine Translation Formality with Synthetic Supervision.** [paper](https://arxiv.org/abs/1911.08706)
*Xing Niu, Marine Carpuat*
**Domain**: Training
10. **Towards Making the Most of BERT in Neural Machine Translation.** [paper](https://arxiv.org/abs/1908.05672)
*Jiacheng Yang, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Yong Yu, Weinan Zhang, Lei Li*
**Domain**: Pre-Training
11. **Acquiring Knowledge from Pre-trained Model to Neural Machine Translation.** [paper](https://arxiv.org/abs/1912.01774)
*Rongxiang Weng, Heng Yu, Shujian Huang1, Shanbo Cheng, Weihua Luo*
**Domain**: Pre-Training
12. **A Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation.** [paper](-)
*Rumeng Li, Xun Wang, Hong Yu*
**Domain**: Low-Resource
13. **Alignment-‐Enhanced Transformer for Constraining NMT with Pre-‐Specified Translations.** [paper](https://www.aaai.org/Papers/AAAI/2020GB/AAAI-SongK.6422.pdf)
*Kai Song, Kun Wang, Heng Yu, Yue Zhang, Zhongqiang Huang, Weihua Luo, Xiangyu Duan, Min Zhang*
**Domain**: Neural Network Architecture
14. **GRET: Global Representation Enhanced Transformer.** [paper](https://arxiv.org/pdf/2002.10101.pdf)
*Rongxiang Weng, Haoran Wei, Shujian Huang, Heng Yu, Lidong Bing, Weihua Luo, Jiajun Chen*
**Domain**: Neural Network Architecture
15. **Explicit Sentence Compression for Neural Machine Translation.** [paper](https://arxiv.org/abs/1912.11980)
*Zuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang, and Hai Zhao*
**Domain**: Neural Network Architecture
16. **Neuron Interaction Based Representation Composition for Neural Machine Translation.** [paper](http://arxiv.org/abs/1911.09877?context=cs.CL)
*Jian Li, Xing Wang, Baosong Yang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu*
**Domain**: Neural Network Architecture
17. **Neural Machine Translation with Joint Representation.** [paper](https://arxiv.org/abs/2002.06546)
*Yanyang Li, Qiang Wang, Tong Xiao, Tongran Liu and Jingbo Zhu*
**Domain**: Neural Network Architecture
18. **IntroVNMT: An Introspective Model for Variational Neural Machine Translation.** [paper](-)
*Xin Sheng, Linli Xu, Junliang Guo, Jingchang Liu, Ruoyu Zhao, Yinlong Xu*
**Domain**: Neural Network Architecture
19. **Cross-lingual Pre-training Based Transfer for Zero-shot Neural Machine Translation.** [paper](https://arxiv.org/abs/1912.01214)
*Baijun Ji, Zhirui Zhang, Xiangyu Duan, Min Zhang, Boxing Chen and Weihua Luo*
**Domain**: Low-resource
20. **Modeling Fluency and Faithfulness for Diverse Neural Machine Translation.** [paper](https://arxiv.org/abs/1912.00178)
*Yang Feng, Wanying Xie, Shuhao Gu, Chenze Shao, Wen Zhang, Zhengxin Yang, Dong Yu*
**Domain**: Decoding
21. **Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation.** [paper](https://arxiv.org/abs/1909.00437)
*Aditya Siddhant, Melvin Johnson, Henry Tsai, Naveen Arivazhagan, Jason Riesa, Ankur Bapna, Orhan Firat, Karthik Raman*
**Domain**: Multilingual NMT
22. **Visual Agreement Regularized Training for Multi-Modal Machine Translation.** [paper](https://arxiv.org/abs/1912.12014)
*Pengcheng Yang, Boxing Chen, Pei Zhang, Xu Sun*
**Domain**: Multi-modal machine translation
23. **Balancing Quality and Human Involvement: an Effective Approach to Interactive Neural Machine Translation.** [paper](-)
*tianxiang zhao, Lemao Liu, Guoping Huang, Zhaopeng Tu, Huayang Li, Yingling Liu, Liu GuiQuan, Shuming Shi*
**Domain**: Interactive Translation
### IJCAI
#### 2019
1. **Correct-and-Memorize: Learning to Translate from Interactive Revisions.** [paper](https://www.ijcai.org/Proceedings/2019/0730.pdf)
*Rongxiang Weng, Hao Zhou, Huang Shujian, Yifan Xia, Lei Li, Jiajun Chen*
**Domain**: interactive translation
2. **Sharing Attention Weights for Fast Transformer.** [paper](https://www.ijcai.org/Proceedings/2019/0735.pdf)
*Tong Xiao, Yinqiao Li, Jingbo Zhu, Zhengtao Yu, Tongran Liu*
**Domain**: Neural Network Architecture
3. **From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots.** [paper](https://www.ijcai.org/Proceedings/2019/0685.pdf)
*Shizhe Chen, Qin Jin, Jianlong Fu*
**Domain**: Low Resource
4. **Polygon-Net: A General Framework for Jointly Boosting Multiple Unsupervised Neural Machine Translation Models.** [paper](https://www.ijcai.org/Proceedings/2019/0739.pdf)
*Chang Xu, Tao Qin, Gang Wang, Tie-Yan Liu*
**Domain**: Unsupervised
### COLING
#### 2018
1. **A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation.** [paper](http://aclweb.org/anthology/C18-1054)
*Surafel M. Lakew, Mauro Cettolo and Marcello Federico*
**Domain**: Problem Analysis
2. **Appraise Evaluation Framework for Machine Translation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-2019/)
*Christian Federmann*
**Domain**: Problem Analysis
3. **On Adversarial Examples for Character-Level Neural Machine Translation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1055/)
*Javid Ebrahimi, Daniel Lowd and Dejing Dou*
**Domain**: Problem Analysis
4. **Neural Machine Translation with Decoding-History Enhanced Attention.** [paper](http://aclweb.org/anthology/C18-1124)
*Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong and Chao bian*
**Domain**: Neural Network Architecture
5. **Refining Source Representations with Relation Networks for Neural Machine Translation.** [paper](https://aclweb.org/anthology/C18-1110)
*Wen Zhang, Jiawei Hu, Yang Feng and Qun Liu*
**Domain**: Neural Network Architecture
6. **Adaptive Weighting for Neural Machine Translation.** [paper](http://aclweb.org/anthology/C18-1257)
*Yachao Li, Junhui Li and Min Zhang*
**Domain**: Neural Network Architecture
7. **Multilingual Neural Machine Translation with Task-Specific Attention.** [paper](http://aclweb.org/anthology/C18-1263)
*Graeme Blackwood, Miguel Ballesteros and Todd Ward*
**Domain**: Neural Network Architecture
8. **Deconvolution-Based Global Decoding for Neural Machine Translation.** [paper](http://aclweb.org/anthology/C18-1276)
*Junyang Lin, Xu Sun, Xuancheng Ren, Shuming Ma, Jinsong Su and Qi Su*
**Domain**: Neural Network Architecture
9. **Improving Neural Machine Translation by Incorporating Hierarchical Subword Features.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1052/)
*Makoto Morishita, Jun Suzuki and Masaaki Nagata*
**Domain**: Neural Network Architecture
10. **Neural Machine Translation with Decoding History Enhanced Attention.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1124/)
*Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong and Chao Bian*
**Domain**: Neural Network Architecture
11. **Neural Machine Translation Incorporating Named Entity.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1274/)
*Arata Ugawa, Akihiro Tamura, Takashi Ninomiya, Hiroya Takamura and Manabu Okumura*
**Domain**: Neural Network Architecture
12. **Multi-layer Representation Fusion for Neural Machine Translation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1255/)
*Qiang Wang, Fuxue Li, Tong Xiao, Yanyang Li, Yinqiao Li and Jingbo Zhu*
**Domain**: Neural Network Architecture
13. **Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches.** [paper](http://aclweb.org/anthology/C18-1050)
*Shaohui Kuang, Deyi Xiong, Weihua Luo and Guodong Zhou*
**Domain**: Context-aware NMT
14. **Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1051/)
*Shaohui Kuang and Deyi Xiong*
**Domain**: Context-aware NMT
15. **A Survey of Domain Adaptation for Neural Machine Translation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1111/)
*Chenhui Chu, Rui Wang*
**Domain**: Domain Adaptation
16. **Sentence Weighting for Neural Machine Translation Domain Adaptation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1269/)
*Shiqi Zhang and Deyi Xiong*
**Domain**: Domain Adaptation
17. **Incorporating Syntactic Uncertainty in Neural Machine Translation with a Forest-to-Sequence Model.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1120/)
*Poorya Zaremoodi and Gholamreza Haffari*
**Domain**: External Knowledge
18. **Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1122/)
*Francis Grégoire and Philippe Langlais*
**Domain**: Data Processing
19. **Parallel Corpora for bi-lingual English-Ethiopian Languages Statistical Machine Translation.** [paper](https://aclweb.org/anthology/papers/C/C18/C18-1262/)
*Solomon Teferra Abate, Michael Melese, Martha Yifiru Tachbelie, Million Meshesha, Solomon Atinafu, Wondwossen Mulugeta, Yaregal Assabie, Hafte Abera, Binyam Ephrem, Tewodros Abebe, Wondimagegnhue Tsegaye, Amanuel Lemma, Tsegaye Andargie and Seifedin Shifaw*
**Domain**: Data Processing
## List by Area
### Deep Transformer
1. **Training Deeper Neural Machine Translation Models with Transparent Attention.** [paper](https://www.aclweb.org/anthology/D18-1338)
*Ankur Bapna, Mia Chen, Orhan Firat, Yuan Cao, Yonghui Wu*
**Venue**: EMNLP-2018
2. **Learning Deep Transformer Models for Machine Translation.** [paper](https://arxiv.org/pdf/1906.01787.pdf)
*Qiang Wang, Bei Li, Tong Xiao, Jingbo Zhu, Changliang Li, Derek F. Wong, Lidia S. Chao*
**Venue**: ACL-2019
3. **Depth Growing for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/P19-1558.pdf)
*Lijun Wu, Yiren Wang, Yingce Xia, Fei Tian, Fei Gao, Tao Qin, Jianhuang Lai, Tie-Yan Liu*
**Venue**: ACL-2019
4. **Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention.** [paper](https://www.aclweb.org/anthology/D19-1083.pdf)
*Biao Zhang, Ivan Titov, Rico Sennrich*
**Venue**: EMNLP-2019
5. **Lipschitz Constrained Parameter Initialization for Deep Transformers.** [paper](https://www.aclweb.org/anthology/2020.acl-main.38.pdf)
*Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Jingyi Zhang*
**Venue**: ACL-2020
6. **Multiscale Collaborative Deep Models for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.40.pdf)
*Xiangpeng Wei, Heng Yu, Yue Hu, Yue Zhang, Rongxiang Weng, Weihua Luo*
**Venue**: ACL-2020
7. **Improving Transformer Optimization Through Better Initialization.** [paper](http://www.cs.toronto.edu/~mvolkovs/ICML2020_tfixup.pdf)
*Xiao Shi Huang, Felipe Perez, Jimmy Ba, Maksims Volkovs*
**Venue**: ICML-2020
8. **Understanding the Difficulty of Training Transformers.** [paper](https://arxiv.org/pdf/2004.08249.pdf)
*Liyuan Liu, Xiaodong Liu, Jianfeng Gao, Weizhu Chen, JIawei Han*
**Venue**: EMNLP-2020
9. **GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.** [paper](https://arxiv.org/pdf/2006.16668.pdf)
*Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, Zhifeng Chen*
**Venue**: arXiv
10. **Character-Level Language Modeling with Deeper Self-Attention.** [paper](https://arxiv.org/abs/1808.04444)
*Rami Al-Rfou, Dokook Choe, Noah Constant, Mandy Guo, Llion Jones*
**Venue**: CoRR
11. **Very Deep Self-Attention Networks for End-to-End Speech Recognition.** [paper](https://arxiv.org/abs/1904.13377)
*Ngoc-Quan Pham, Thai-Son Nguyen, Jan Niehues, Markus Muller, Sebastian Stuker, Alexander Waibel*
**Venue**: CoRR
12. **Shallow-to-Deep Training for Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.emnlp-main.72.pdf)
*Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, Jingbo Zhu*
**Venue**: EMNLP-2020
13. **Learning Light-Weight Translation Models from Deep Transformer.** [paper]()
*Bei Li, Ziyang Wang, Hui Liu, Quan Du, Tong Xiao, Chunliang Zhang, Jingbo Zhu*
**Venue**: AAAI-2021
### Fast RNN
1. **A Lightweight Recurrent Network for Sequence Modeling.** [paper](https://arxiv.org/abs/1905.13324)
*Biao Zhang, Rico Sennrich*
**Venue**: ACL-2019
2. **Simple Recurrent Units for Highly Parallelizable Recurrence.** [paper](https://arxiv.org/abs/1709.02755)
*Tao Lei, Yu Zhang, Sida I. Wang, Hui Dai, Yoav Artzi*
**Venue**: EMNLP-2018
3. **Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks.** [paper](https://arxiv.org/abs/1810.12546)
*Biao Zhang, Deyi Xiong, Jinsong Su, Qian Lin, Huiji Zhang*
**Venue**: EMNLP-2018
### Knowledge Distillation of BERT
1. **Patient Knowledge Distillation for BERT Model Compression.** [paper](https://www.aclweb.org/anthology/D19-1441.pdf)
*Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu*
**Venue**: EMNLP 2019
2. **ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.** [paper](https://arxiv.org/abs/1909.11942)
*Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut*
**Venue**: ICLR 2020
3. **TinyBERT: Distilling BERT for Natural Language Understanding.** [paper](https://arxiv.org/abs/1909.10351)
*Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, Qun Liu*
**Venue**: arxiv
4. **DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.** [paper](https://arxiv.org/abs/1910.01108)
*Victor Sanh, Lysandre Debut, Julien Chaumond, Thomas Wolf*
**Venue**: NeurlPS 2019
### None Autoregressive Translation
1. **Patient Knowledge Distillation for BERT Model Compression.** [paper](https://www.aclweb.org/anthology/D19-1441.pdf)
*Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu*
**Venue**: EMNLP 2019
2. **ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.** [paper](https://arxiv.org/abs/1909.11942)
*Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut*
**Venue**: ICLR 2020
3. **TinyBERT: Distilling BERT for Natural Language Understanding.** [paper](https://arxiv.org/abs/1909.10351)
*Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, Qun Liu*
**Venue**: arxiv
4. **DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.** [paper](https://arxiv.org/abs/1910.01108)
*Victor Sanh, Lysandre Debut, Julien Chaumond, Thomas Wolf*
**Venue**: NeurlPS 2019
1. **Non-Autoregressive Neural Machine Translation.** [paper](https://arxiv.org/abs/1711.02281)
*Jiatao Gu, James Bradbury, Caiming Xiong, Victor O. K. Li, Richard Socher*
**Venue**: ICLR-2018
2. **Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement.** [paper](https://doi.org/10.18653/v1/d18-1149)
*Jason Lee, Elman Mansimov, Kyunghyun Cho*
**Venue**: EMNLP-2018
3. **End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification.** [paper](https://doi.org/10.18653/v1/d18-1336)
*Jindrich Libovický, Jindrich Helcl*
**Venue**: EMNLP-2018
4. **Fast Decoding in Sequence Models Using Discrete Latent Variables.** [paper](https://arxiv.org/pdf/1803.03382.pdf)
*Lukasz Kaiser, Samy Bengio, Aurko Roy, Ashish Vaswani, Niki Parmar, Jakob Uszkoreit, Noam Shazeer*
**Venue**: ICML-2018
5. **Imitation Learning for Non-Autoregressive Neural Machine Translation.** [paper](https://doi.org/10.18653/v1/p19-1125)
*Bingzhen Wei, Mingxuan Wang, Hao Zhou, Junyang Lin, Xu Sun*
**Venue**: ACL-2019
6. **Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation.** [paper](https://doi.org/10.18653/v1/p19-1288)
*Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen, Jie Zhou*
**Venue**: ACL-2019
7. **Syntactically Supervised Transformers for Faster Neural Machine Translation.** [paper](https://doi.org/10.18653/v1/p19-1122)
*Nader Akoury, Kalpesh Krishna, Mohit Iyyer*
**Venue**: ACL-2019
8. **Non-Autoregressive Machine Translation with Auxiliary Regularization.** [paper](https://doi.org/10.1609/aaai.v33i01.33015377)
*Yiren Wang, Fei Tian, Di He, Tao Qin, ChengXiang Zhai, Tie-Yan Liu*
**Venue**: AAAI-2019
9. **Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input.** [paper](https://doi.org/10.1609/aaai.v33i01.33013723)
*Junliang Guo, Xu Tan, Di He, Tao Qin, Linli Xu, Tie-Yan Liu*
**Venue**: AAAI-2019
10. **Mask-Predict: Parallel Decoding of Conditional Masked Language Models.** [paper](https://doi.org/10.18653/v1/D19-1633)
*Marjan Ghazvininejad, Omer Levy, Yinhan Liu, Luke Zettlemoyer*
**Venue**: EMNLP-2019
11. **Insertion-based Decoding with Automatically Inferred Generation Order.** [paper](https://transacl.org/ojs/index.php/tacl/article/view/1732)
*Jiatao Gu, Qi Liu, Kyunghyun Cho*
**Venue**: TACL-2019
12. **Fast Structured Decoding for Sequence Models.** [paper](http://papers.nips.cc/paper/8566-fast-structured-decoding-for-sequence-models)
*Zhiqing Sun, Zhuohan Li, Haoqing Wang, Di He, Zi Lin, Zhi-Hong Deng*
**Venue**: NeurIPS-2019
13. **Levenshtein Transformer.** [paper](https://papers.nips.cc/paper/9297-levenshtein-transformer)
*Jiatao Gu, Changhan Wang, Junbo Zhao*
**Venue**: NeurIPS-2019
14. **Hint-Based Training for Non-Autoregressive Machine Translation.** [paper](https://doi.org/10.18653/v1/D19-1573)
*Zhuohan Li, Zi Lin, Di He, Fei Tian, Tao Qin, Liwei Wang, Tie-Yan Liu*
**Venue**: EMNLP-2019
15. **FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow.** [paper](https://doi.org/10.18653/v1/D19-1437)
*Xuezhe Ma, Chunting Zhou, Xian Li, Graham Neubig, Eduard H. Hovy*
**Venue**: EMNLP-2019
16. **Improving Non-autoregressive Neural Machine Translation with Monolingual Data.** [paper](https://www.aclweb.org/anthology/2020.acl-main.171)
*Jiawei Zhou, Phillip Keung*
**Venue**: ACL-2020
17. **Parallel Machine Translation with Disentangled Context Transformer.** [paper](https://arxiv.org/abs/2001.05136)
*Jungo Kasai, James Cross, Marjan Ghazvininejad, Jiatao Gu*
**Venue**: ICML-2020
18. **Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.36)
*Junliang Guo, Linli Xu, Enhong Chen*
**Venue**: ACL-2020
19. **A Study of Non-autoregressive Model for Sequence Generation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.15)
*Yi Ren, Jinglin Liu, Xu Tan, Zhou Zhao, Sheng Zhao, Tie-Yan Liu*
**Venue**: ACL-2020
20. **Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.277)
*Qiu Ran, Yankai Lin, Peng Li, Jie Zhou*
**Venue**: ACL-2020
21. **ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation.** [paper](https://www.aclweb.org/anthology/2020.acl-main.251)
*Lifu Tu, Richard Yuanzhe Pang, Sam Wiseman, Kevin Gimpel*
**Venue**: ACL-2020
22. **Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior.** [paper](https://aaai.org/ojs/index.php/AAAI/article/view/6413)
*Raphael Shu, Jason Lee, Hideki Nakayama, Kyunghyun Cho*
**Venue**: AAAI-2020
23. **Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation.** [paper](https://aaai.org/ojs/index.php/AAAI/article/view/5351)
*Chenze Shao, Jinchao Zhang, Yang Feng, Fandong Meng and Jie Zhou*
**Venue**: AAAI-2020
24. **Understanding Knowledge Distillation in Non-autoregressive Machine Translation.** [paper](https://openreview.net/forum?id=BygFVAEKDH)
*Chunting Zhou, Jiatao Gu, Graham Neubig*
**Venue**: ICLR-2020
25. **Aligned Cross Entropy for Non-Autoregressive Machine Translation.** [paper](https://doi.org/10.18653/v1/p19-1122)
*Marjan Ghazvininejad, Vladimir Karpukhin, Luke Zettlemoyer, Omer Levy*
**Venue**: ICML-2020
26. **Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation.** [paper](https://aaai.org/ojs/index.php/AAAI/article/view/6289)
*Junliang Guo, Xu Tan, Linli Xu, Tao Qin, Enhong Chen, Tie-Yan Liu*
**Venue**: AAAI-2020
27. **Non-Autoregressive Machine Translation with Latent Alignments.** [paper](https://arxiv.org/abs/2004.07437)
*Chitwan Saharia, William Chan, Saurabh Saxena, Mohammad Norouzi*
**Venue**: CoRR
28. **Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information.** [paper](http://arxiv.org/abs/1911.02215)
*Qiu Ran, Yankai Lin, Peng Li, Jie Zhou*
**Venue**: CoRR
29. **LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention.** [paper](https://arxiv.org/abs/2002.03084)
*Xiaoya Li, Yuxian Meng, Arianna Yuan, Fei Wu, Jiwei Li*
**Venue**: CoRR
30. **Improving Fluency of Non-Autoregressive Machine Translation.** [paper](https://arxiv.org/abs/2004.03227)
*Zdenek Kasner, Jindrich Libovický, Jindrich Helcl*
**Venue**: CoRR