\parinterval BERT的核心思想是通过{\small\bfnew{掩码语言模型}}（Masked Language Model，MLM）\index{掩码语言模型}\index{MLM}任务进行预训练。掩码语言模型的思想类似于完形填空，随机选择输入句子中的部分词掩码，之后让模型预测这些被掩码的词。掩码的具体做法是将被选中的词替换为一个特殊的词[Mask]，这样模型在训练过程中，无法得到掩码位置词的信息，需要联合上下文内容进行预测，因此提高了模型对上下文的特征提取能力。实验表明，相比在下游任务中仅利用上下文词嵌入，在大规模单语数据上预训练的模型具有更强的表示能力。而使用掩码的方式进行训练也给神经机器翻译提供了新的思路，在本章中也会使用到类似方法。
\parinterval多语言单模型方法也可以被看做是一种迁移学习。多语言单模型方法能够有效地改善低资源神经机器翻译性能\upcite{DBLP:journals/tacl/JohnsonSLKWCTVW17,DBLP:conf/lrec/RiktersPK18,dabre2020survey}，尤其适用于翻译方向较多的情况，因为为每一个翻译方向单独训练一个模型是不实际的，不仅因为设备资源和时间上的限制，还因为很多翻译方向都没有双语平行数据。比如，要翻译100个语言之间互译的系统，理论上就需要训练$100\times99$个翻译模型，代价是十分巨大的。这时就需要用到{\small\bfnew{多语言单模型方法}}\index{多语言单模型方法}（Multi-lingual Single Model-based Method\index{Multi-lingual Single Model-based Method}）。
\parinterval{\small\bfnew{多语言单模型方法}}\index{多语言单模型方法}（Multi-lingual Single Model-based Method\index{Multi-lingual Single Model-based Method}）也可以被看做是一种迁移学习。多语言单模型方法能够有效地改善低资源神经机器翻译性能\upcite{DBLP:journals/tacl/JohnsonSLKWCTVW17,DBLP:conf/lrec/RiktersPK18,dabre2020survey}，尤其适用于翻译方向较多的情况，因为为每一个翻译方向单独训练一个模型是不实际的，不仅因为设备资源和时间上的限制，还因为很多翻译方向都没有双语平行数据。比如，要翻译100个语言之间互译的系统，理论上就需要训练$100\times99$个翻译模型，代价是十分巨大的。这时就需要用到多语言单模型方法。
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{DBLP:conf/acl/LiLWJXZLL20,
author = {Bei Li and
Hui Liu and
...
...
@@ -4679,15 +4655,6 @@ author = {Yoshua Bengio and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:journals/corr/LuongPM15,
author = {Thang Luong and
Hieu Pham and
Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1412--1421},
year = {2015}
}
@inproceedings{He2016ImprovedNM,
author = {Wei He and
Zhongjun He and
...
...
@@ -4775,19 +4742,6 @@ author = {Yoshua Bengio and
pages = {21--37},
year = {2016}
}
@inproceedings{devlin-etal-2014-fast,
author = {Jacob Devlin and
Rabih Zbib and
Zhongqiang Huang and
Thomas Lamar and
Richard M. Schwartz and
John Makhoul},
title = {Fast and Robust Neural Network Joint Models for Statistical Machine
Translation},
pages = {1370--1380},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/acl/WangLLJL15,
author = {Mingxuan Wang and
Zhengdong Lu and
...
...
@@ -4818,15 +4772,6 @@ author = {Yoshua Bengio and
publisher = {International Conference on Acoustics, Speech and Signal Processing},
year = {2013}
}
@inproceedings{DBLP:journals/corr/LuongPM15,
author = {Thang Luong and
Hieu Pham and
Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1412--1421},
year = {2015}
}
@inproceedings{DBLP:conf/acl-codeswitch/WangCK18,
author = {Changhan Wang and
Kyunghyun Cho and
...
...
@@ -4879,15 +4824,6 @@ author = {Yoshua Bengio and
publisher = {Springer},
year = {2017}
}
@inproceedings{2011Natural,
title={Natural Language Processing (almost) from Scratch},
author={ Collobert, Ronan and Weston, Jason and Bottou, Léon and Karlen, Michael and Kavukcuoglu, Koray and Kuksa, Pavel },
publisher={Journal of Machine Learning Research},
volume={12},
number={1},
pages={2493-2537},
year={2011},
}
@inproceedings{DBLP:conf/acl/NguyenG15,
author = {Thien Huu Nguyen and
Ralph Grishman},
...
...
@@ -4943,14 +4879,6 @@ author = {Yoshua Bengio and
publisher = {Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{StahlbergNeural,
title={Neural Machine Translation: A Review},
author={Felix Stahlberg},
publisher={Journal of Artificial Intelligence Research},
year={2020},
volume={69},
pages={343-418}
}
@inproceedings{Sennrich2016ImprovingNM,
author = {Rico Sennrich and
Barry Haddow and
...
...
@@ -4959,14 +4887,6 @@ author = {Yoshua Bengio and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{Waibel1989PhonemeRU,
title={Phoneme recognition using time-delay neural networks},
author={Alexander Waibel and Toshiyuki Hanazawa and Geoffrey Hinton and Kiyohiro Shikano and Kevin J. Lang},
...
...
@@ -5002,30 +4922,6 @@ author = {Yoshua Bengio and
pages = {770--778},
year = {2016}
}
@inproceedings{DBLP:conf/cvpr/HuangLMW17,
author = {Gao Huang and
Zhuang Liu and
Laurens van der Maaten and
Kilian Q. Weinberger},
title = {Densely Connected Convolutional Networks},
pages = {2261--2269},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{Girshick2015FastR,
title={Fast R-CNN},
author={Ross Girshick},
publisher={International Conference on Computer Vision},
year={2015},
pages={1440-1448}
}
@inproceedings{He2020MaskR,
title={Mask R-CNN},
author={Kaiming He and Georgia Gkioxari and Piotr Doll{\'a}r and Ross B. Girshick},
publisher={International Conference on Computer Vision},
pages={2961--2969},
year={2017}
}
@inproceedings{Kalchbrenner2014ACN,
title={A Convolutional Neural Network for Modelling Sentences},
author={Nal Kalchbrenner and Edward Grefenstette and Phil Blunsom},
...
...
@@ -5079,18 +4975,6 @@ author = {Yoshua Bengio and
pages = {123--135},
year={2017}
}
@inproceedings{DBLP:journals/corr/GehringAGYD17,
author = {Jonas Gehring and
Michael Auli and
David Grangier and
Denis Yarats and
Yann N. Dauphin},
title = {Convolutional Sequence to Sequence Learning},
publisher = {International Conference on Machine Learning},
volume = {70},
pages = {1243--1252},
year = {2017}
}
@inproceedings{Kaiser2018DepthwiseSC,
title={Depthwise Separable Convolutions for Neural Machine Translation},
author = {Lukasz Kaiser and
...
...
@@ -5109,14 +4993,6 @@ author = {Yoshua Bengio and
publisher = {International Conference on Learning Representations},
title = {Recurrent Continuous Translation Models},
pages = {1700--1709},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2013}
}
@inproceedings{Wu2016GooglesNM,
title={Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
author = {Yonghui Wu and
...
...
@@ -5154,16 +5030,6 @@ author = {Yoshua Bengio and
year={2016},
volume={abs/1609.08144}
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016},
}
@inproceedings{Sukhbaatar2015EndToEndMN,
title={End-To-End Memory Networks},
author = {Sainbayar Sukhbaatar and
...
...
@@ -5326,13 +5192,6 @@ author = {Yoshua Bengio and
volume = {abs/1802.05751},
year = {2018}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{DBLP:conf/iclr/WuLLLH20,
author = {Zhanghao Wu and
Zhijian Liu and
...
...
@@ -5377,24 +5236,6 @@ author = {Yoshua Bengio and
pages = {464--468},
year = {2018},
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016},
}
@inproceedings{JMLR:v15:srivastava14a,
author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
publisher = {Journal of Machine Learning Research},
year = {2014},
volume = {15},
pages = {1929-1958},
}
@inproceedings{Szegedy_2016_CVPR,
author = {Christian Szegedy and
Vincent Vanhoucke and
...
...
@@ -5424,28 +5265,6 @@ author = {Yoshua Bengio and
volume = {abs/1602.02830},
year = {2016},
}
@inproceedings{Wu2019PayLA,
author = {Felix Wu and
Angela Fan and
Alexei Baevski and
Yann N. Dauphin and
Michael Auli},
title = {Pay Less Attention with Lightweight and Dynamic Convolutions},
publisher = {International Conference on Learning Representations},
year = {2019},
}
@inproceedings{dai-etal-2019-transformer,
author = {Zihang Dai and
Zhilin Yang and
Yiming Yang and
Jaime G. Carbonell and
Quoc Viet Le and
Ruslan Salakhutdinov},
title = {Transformer-XL: Attentive Language Models beyond a Fixed-Length Context},
pages = {2978--2988},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{Liu2020LearningTE,
title={Learning to Encode Position for Transformer with Continuous Dynamical Model},
author={Xuanqing Liu and Hsiang-Fu Yu and Inderjit Dhillon and Cho-Jui Hsieh},
...
...
@@ -5620,14 +5439,6 @@ author = {Yoshua Bengio and
publisher = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2012}
}
@inproceedings{JMLR:v15:srivastava14a,
author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
publisher = {Journal of Machine Learning Research},
year = {2014},
volume = {15},
pages = {1929-1958},
}
@inproceedings{DBLP:conf/amta/MullerRS20,
author = {Mathias M{\"{u}}ller and
Annette Rios and
...
...
@@ -5834,21 +5645,6 @@ author = {Yoshua Bengio and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/LiLWJXZLL20,
author = {Bei Li and
Hui Liu and
Ziyang Wang and
Yufan Jiang and
Tong Xiao and
Jingbo Zhu and
Tongran Liu and
Changliang Li},
title = {Does Multi-Encoder Help? {A} Case Study on Context-Aware Neural Machine
Translation},
pages = {3512--3518},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@techreport{chen1999gaussian,
title={A Gaussian prior for smoothing maximum entropy models},
author={Chen, Stanley F and Rosenfeld, Ronald},
...
...
@@ -5863,14 +5659,6 @@ author = {Yoshua Bengio and
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/icassp/SchusterN12,
author = {Mike Schuster and
Kaisuke Nakajima},
title = {Japanese and Korean voice search},
pages = {5149--5152},
publisher = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2012}
}
@inproceedings{kudo2018sentencepiece,
title={SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing},
author={Taku {Kudo} and John {Richardson}},
...
...
@@ -6166,12 +5954,6 @@ author = {Yoshua Bengio and
publisher = {Conference on Computational Learning Theory},
year = {1992}
}
@book{mitchell1996m,
title={Machine Learning},
author={Mitchell, Tom},
journal={McCraw Hill},
year={1996}
}
@inproceedings{DBLP:conf/icml/AbeM98,
author = {Naoki Abe and
Hiroshi Mamitsuka},
...
...
@@ -6195,15 +5977,6 @@ author = {Yoshua Bengio and
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2005}
}
@inproceedings{726791,
author={Yann {Lecun} and Leon {Bottou} and Yoshua {Bengio} and Patrick {Haffner}},
publisher={Proceedings of the IEEE},
title={Gradient-based learning applied to document recognition},
year={1998},
volume={86},
number={11},
pages={2278-2324}
}
@book{atkinson2007optimum,
title={Optimum experimental designs, with SAS},
author={Atkinson, Anthony and Donev, Alexander and Tobias, Randall and others},
...
...
@@ -6245,16 +6018,6 @@ author = {Yoshua Bengio and
publisher = {{IEEE} Winter Conference on Applications of Computer Vision},
year = {2020}
}
@inproceedings{DBLP:conf/acl/JeanCMB15,
author = {S{\'{e}}bastien Jean and
KyungHyun Cho and
Roland Memisevic and
Yoshua Bengio},
title = {On Using Very Large Target Vocabulary for Neural Machine Translation},
pages = {1--10},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{2015OnGulcehre,
title = {On Using Monolingual Corpora in Neural Machine Translation},
author = {Gulcehre Caglar and
...
...
@@ -6269,14 +6032,6 @@ author = {Yoshua Bengio and
publisher = {Computer Science},
year = {2015},
}
@inproceedings{Sennrich2016ImprovingNM,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Improving Neural Machine Translation Models with Monolingual Data},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/aaai/Zhang0LZC18,
author = {Zhirui Zhang and
Shujie Liu and
...
...
@@ -6641,16 +6396,6 @@ author = {Yoshua Bengio and
pages = {1171--1179},
year = {2015}
}
@inproceedings{Bengio2015ScheduledSF,
title={Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks},
author={Samy Bengio and
Oriol Vinyals and
Navdeep Jaitly and
Noam Shazeer},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {1171--1179},
year = {2015}
}
@inproceedings{Ranzato2016SequenceLT,
title={Sequence Level Training with Recurrent Neural Networks},
author={Marc'Aurelio Ranzato and
...
...
@@ -6674,43 +6419,6 @@ author = {Yoshua Bengio and
pages = {2672--2680},
year = {2014}
}
@inproceedings{DBLP:conf/acl/ShenCHHWSL16,
author = {Shiqi Shen and
Yong Cheng and
Zhongjun He and
Wei He and
Hua Wu and
Maosong Sun and
Yang Liu},
title = {Minimum Risk Training for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/acl/PapineniRWZ02,
author = {Kishore Papineni and
Salim Roukos and
Todd Ward and
Wei-jing Zhu},
title = {Bleu: a Method for Automatic Evaluation of Machine Translation},
pages = {311--318},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002}
}
@inproceedings{doddington2002automatic,
title={Automatic evaluation of machine translation quality using n-gram co-occurrence statistics},
publisher={Proceedings of the second international conference on Human Language Technology Research},
author={Doddington, George},
pages={138--145},
year={2002}
}
@inproceedings{snover2006study,
title={A study of translation edit rate with targeted human annotation},
author={Snover, Matthew and Dorr, Bonnie and Schwartz, Richard and Micciulla, Linnea and Makhoul, John},
publisher={Proceedings of association for machine translation in the Americas},
volume={200},
number={6},
year={2006}
}
@inproceedings{lavie2009meteor,
title={The METEOR metric for automatic evaluation of machine translation},
author={Lavie, Alon and Denkowski, Michael J},
...
...
@@ -6720,36 +6428,6 @@ author = {Yoshua Bengio and
pages={105--115},
year={2009}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{koehn2003statistical,
author = {Philipp Koehn and
Franz Josef Och and
Daniel Marcu},
title = {Statistical Phrase-Based Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{smith2006minimum,
author = {David A. Smith and
Jason Eisner},
title = {Minimum Risk Annealing for Training Log-Linear Models},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{he2012maximum,
title={Maximum expected bleu training of phrase and lexicon translation models},
author={He, Xiaodong and Deng, Li},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={292--301},
year={2012}
}
@inproceedings{DBLP:conf/acl/GaoHYD14,
author = {Jianfeng Gao and
Xiaodong He and
...
...
@@ -6907,14 +6585,6 @@ year={2012}
volume = {abs/2002.11794},
year = {2020}
}
@inproceedings{kim-rush-2016-sequence,
author = {Yoon Kim and
Alexander M. Rush},
title = {Sequence-Level Knowledge Distillation},
pages = {1317--1327},
publisher = {Conference on Empirical Methods in Natural Language Processing},
title = {Moses: Open Source Toolkit for Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/amta/Koehn04,
author = {Philipp Koehn},
title = {Pharaoh: {A} Beam Search Decoder for Phrase-Based Statistical Machine
Translation Models},
volume = {3265},
pages = {115--124},
publisher = { Association for Machine Translation in the Americas},
year = {2004}
}
@inproceedings{DBLP:conf/emnlp/StahlbergHSB17,
author = {Felix Stahlberg and
Eva Hasler and
...
...
@@ -7189,16 +6831,6 @@ year={2012}
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/HuangZM17,
author = {Liang Huang and
Kai Zhao and
Mingbo Ma},
title = {When to Finish? Optimal Beam Search for Neural Text Generation (modulo
beam size)},
pages = {2134--2139},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{Wiseman2016SequencetoSequenceLA,
title={Sequence-to-Sequence Learning as Beam-Search Optimization},
author={Sam Wiseman and Alexander M. Rush},
...
...
@@ -7206,16 +6838,6 @@ year={2012}
pages={1296--1306},
year={2016}
}
@inproceedings{DBLP:conf/emnlp/Yang0M18,
author = {Yilin Yang and
Liang Huang and
Mingbo Ma},
title = {Breaking the Beam Search Curse: {A} Study of (Re-)Scoring Methods
and Stopping Criteria for Neural Machine Translation},
pages = {3054--3059},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{Ma2019LearningTS,
title={Learning to Stop in Structured Prediction for Neural Machine Translation},
author={Mingbo Ma and
...
...
@@ -7236,14 +6858,6 @@ year={2012}
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{Jiang2012LearnedPF,
title={Learned Prioritization for Trading Off Accuracy and Speed},
author={Jiarong Jiang and Adam R. Teichert and Hal Daum{\'e} and Jason Eisner},
...
...
@@ -7379,33 +6993,6 @@ year={2012}
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2017}
}
@inproceedings{StahlbergNeural,
title={Neural Machine Translation: A Review},
author={Felix Stahlberg},
publisher={Journal of Artificial Intelligence Research},
year={2020},
volume={69},
pages={343-418}
}
@inproceedings{Ranzato2016SequenceLT,
title={Sequence Level Training with Recurrent Neural Networks},
author={Marc'Aurelio Ranzato and
Sumit Chopra and
Michael Auli and
Wojciech Zaremba},
publisher={International Conference on Learning Representations},
year={2016}
}
@inproceedings{Bengio2015ScheduledSF,
title={Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks},
author={Samy Bengio and
Oriol Vinyals and
Navdeep Jaitly and
Noam Shazeer},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {1171--1179},
year = {2015}
}
@inproceedings{Zhang2019BridgingTG,
title={Bridging the Gap between Training and Inference for Neural Machine Translation},
author={Wen Zhang and Yang Feng and Fandong Meng and Di You and Qun Liu},
...
...
@@ -7413,55 +7000,6 @@ year={2012}
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ShenCHHWSL16,
author = {Shiqi Shen and
Yong Cheng and
Zhongjun He and
Wei He and
Hua Wu and
Maosong Sun and
Yang Liu},
title = {Minimum Risk Training for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/acl/SennrichHB16a,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Neural Machine Translation of Rare Words with Subword Units},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/emnlp/ZensSX12,
author = {Richard Zens and
Daisy Stanton and
Peng Xu},
title = {A Systematic Comparison of Phrase Table Pruning Techniques},
pages = {972--983},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/emnlp/JohnsonMFK07,
author = {Howard Johnson and
Joel D. Martin and
George F. Foster and
Roland Kuhn},
title = {Improving Translation Quality by Discarding Most of the Phrasetable},
pages = {967--975},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/emnlp/LingGTB12,
author = {Wang Ling and
Jo{\~{a}}o Gra{\c{c}}a and
Isabel Trancoso and
Alan W. Black},
title = {Entropy-based Pruning for Phrase-based Machine Translation},
pages = {962--971},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{Narang2017BlockSparseRN,
title={Block-Sparse Recurrent Neural Networks},
author={Sharan Narang and Eric Undersander and Gregory Diamos},
...
...
@@ -7483,31 +7021,10 @@ year={2012}
author = {Paul Michel and
Omer Levy and
Graham Neubig},
title = {Are Sixteen Heads Really Better than One?},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {14014--14024},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1905-09418,
author = {Elena Voita and
David Talbot and
Fedor Moiseev and
Rico Sennrich and
Ivan Titov},
title = {Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy
Lifting, the Rest Can Be Pruned},
pages = {5797--5808},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019},
}
@inproceedings{Kitaev2020ReformerTE,
author = {Nikita Kitaev and
Lukasz Kaiser and
Anselm Levskaya},
title = {Reformer: The Efficient Transformer},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{Katharopoulos2020TransformersAR,
title={Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention},
author={Angelos Katharopoulos and Apoorv Vyas and Nikolaos Pappas and Franccois Fleuret},
...
...
@@ -7515,15 +7032,6 @@ year={2012}
year={2020},
volume={abs/2006.16236}
}
@inproceedings{xiao2011language,
title ={Language Modeling for Syntax-Based Machine Translation Using Tree Substitution Grammars: A Case Study on Chinese-English Translation},
author ={Xiao, Tong and Zhu, Jingbo and Zhu, Muhua},
volume ={10},
number ={4},
pages ={1--29},
year ={2011},
publisher ={ACM Transactions on Asian Language Information Processing (TALIP)}
}
@inproceedings{Li2009VariationalDF,
title={Variational Decoding for Statistical Machine Translation},
author={Zhifei Li and
...
...
@@ -7558,18 +7066,6 @@ year={2012}
pages={5488--5495},
year={2018}
}
@inproceedings{DBLP:journals/corr/GehringAGYD17,
author = {Jonas Gehring and
Michael Auli and
David Grangier and
Denis Yarats and
Yann N. Dauphin},
title = {Convolutional Sequence to Sequence Learning},
publisher = {International Conference on Machine Learning},
volume = {70},
pages = {1243--1252},
year = {2017}
}
@inproceedings{Wei2019ImitationLF,
title={Imitation Learning for Non-Autoregressive Neural Machine Translation},
author={Bingzhen Wei and Mingxuan Wang and Hao Zhou and Junyang Lin and Xu Sun},
...
...
@@ -7717,15 +7213,6 @@ author = {Zhuang Liu and
volume={18},
pages={187:1-187:30}
}
@inproceedings{DBLP:journals/corr/HintonVD15,
author = {Geoffrey E. Hinton and
Oriol Vinyals and
Jeffrey Dean},
title = {Distilling the Knowledge in a Neural Network},
publisher = {CoRR},
volume = {abs/1503.02531},
year = {2015}
}
@inproceedings{Munim2019SequencelevelKD,
title={Sequence-level Knowledge Distillation for Model Compression of Attention-based Sequence-to-sequence Speech Recognition},
author={Raden Mu'az Mun'im and Nakamasa Inoue and Koichi Shinoda},
...
...
@@ -7746,20 +7233,6 @@ author = {Zhuang Liu and
volume = {abs/1903.12136},
year = {2019}
}
@inproceedings{Jiao2020TinyBERTDB,
author = {Xiaoqi Jiao and
Yichun Yin and
Lifeng Shang and
Xin Jiang and
Xiao Chen and
Linlin Li and
Fang Wang and
Qun Liu},
title = {TinyBERT: Distilling {BERT} for Natural Language Understanding},
pages = {4163--4174},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2020}
}
@inproceedings{Ghazvininejad2020AlignedCE,
author = {Marjan Ghazvininejad and
Vladimir Karpukhin and
...
...
@@ -7816,23 +7289,6 @@ author = {Zhuang Liu and
volume = {abs/1911.02215},
year = {2019}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{Gu2017NonAutoregressiveNM,
author = {Jiatao Gu and
James Bradbury and
Caiming Xiong and
Victor O. K. Li and
Richard Socher},
title = {Non-Autoregressive Neural Machine Translation},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{Zhou2020UnderstandingKD,
title={Understanding Knowledge Distillation in Non-autoregressive Machine Translation},
author={Chunting Zhou and Graham Neubig and Jiatao Gu},
...
...
@@ -7941,13 +7397,6 @@ author = {Zhuang Liu and
volume={7},
pages={91-105}
}
@inproceedings{devlin2019bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin Jacob and Chang Ming-Wei and Lee Kenton and Toutanova Kristina},
year={2019},
pages = {4171--4186},
publisher = {Annual Meeting of the Association for Computational Linguistics},
}
@inproceedings{Feng2016ImprovingAM,
title={Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation},
author={Shi Feng and Shujie Liu and Nan Yang and Mu Li and Ming Zhou and Kenny Q. Zhu},
...
...
@@ -7955,65 +7404,6 @@ author = {Zhuang Liu and
pages={3082--3092},
year={2016}
}
@inproceedings{TuModeling,
author = {Zhaopeng Tu and
Zhengdong Lu and
Yang Liu and
Xiaohua Liu and
Hang Li},
title = {Modeling Coverage for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Wu2016GooglesNM,
title={Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
author = {Yonghui Wu and
Mike Schuster and
Zhifeng Chen and
Quoc V. Le and
Mohammad Norouzi and
Wolfgang Macherey and
Maxim Krikun and
Yuan Cao and
Qin Gao and
Klaus Macherey and
Jeff Klingner and
Apurva Shah and
Melvin Johnson and
Xiaobing Liu and
Lukasz Kaiser and
Stephan Gouws and
Yoshikiyo Kato and
Taku Kudo and
Hideto Kazawa and
Keith Stevens and
George Kurian and
Nishant Patil and
Wei Wang and
Cliff Young and
Jason Smith and
Jason Riesa and
Alex Rudnick and
Oriol Vinyals and
Greg Corrado and
Macduff Hughes and
Jeffrey Dean},
publisher = {CoRR},
year={2016},
volume={abs/1609.08144}
}
@inproceedings{li-etal-2018-simple,
author = {Yanyang Li and
Tong Xiao and
Yinqiao Li and
Qiang Wang and
Changming Xu and
Jingbo Zhu},
title = {A Simple and Effective Approach to Coverage-Aware Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {292--297},
year = {2018}
}
@inproceedings{Peris2017InteractiveNM,
title={Interactive neural machine translation},
author={{\'A}lvaro Peris and Miguel Domingo and F. Casacuberta},
...
...
@@ -8022,13 +7412,6 @@ author = {Zhuang Liu and
volume={45},
pages={201-220}
}
@inproceedings{Peris2018ActiveLF,
title={Active Learning for Interactive Neural Machine Translation of Data Streams},
author={{\'A}lvaro Peris and Francisco Casacuberta},
publisher={The SIGNLL Conference on Computational Natural Language Learning},
pages={151--160},
year={2018}
}
@inproceedings{Xiao2016ALA,
title={A Loss-Augmented Approach to Training Syntactic Machine Translation Systems},
author={Tong Xiao and Derek F. Wong and Jingbo Zhu},
...
...
@@ -8037,16 +7420,6 @@ author = {Zhuang Liu and
volume={24},
pages={2069-2083}
}
@inproceedings{DBLP:conf/acl/JeanCMB15,
author = {S{\'{e}}bastien Jean and
KyungHyun Cho and
Roland Memisevic and
Yoshua Bengio},
title = {On Using Very Large Target Vocabulary for Neural Machine Translation},
pages = {1--10},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{61115,
author={Jianhua Lin},
publisher={IEEE Transactions on Information Theory},
...
...
@@ -8065,73 +7438,6 @@ author = {Zhuang Liu and
publisher = { AAAI Conference on Artificial Intelligence},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1805-00631,
author = {Biao Zhang and
Deyi Xiong and
Jinsong Su},
title = {Accelerating Neural Transformer via an Average Attention Network},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1789--1798},
year = {2018},
}
@inproceedings{Wu2019PayLA,
author = {Felix Wu and
Angela Fan and
Alexei Baevski and
Yann N. Dauphin and
Michael Auli},
title = {Pay Less Attention with Lightweight and Dynamic Convolutions},
publisher = {International Conference on Learning Representations},
year = {2019},
}
@inproceedings{Xiao2019SharingAW,
author = {Tong Xiao and
Yinqiao Li and
Jingbo Zhu and
Zhengtao Yu and
Tongran Liu},
title = {Sharing Attention Weights for Fast Transformer},
publisher = {International Joint Conference on Artificial Intelligence},
pages = {5292--5298},
year = {2019}
}
@inproceedings{Chen2018TheBO,
author = {Mia Xu Chen and
Orhan Firat and
Ankur Bapna and
Melvin Johnson and
Wolfgang Macherey and
George F. Foster and
Llion Jones and
Mike Schuster and
Noam Shazeer and
Niki Parmar and
Ashish Vaswani and
Jakob Uszkoreit and
Lukasz Kaiser and
Zhifeng Chen and
Yonghui Wu and
Macduff Hughes},
title = {The Best of Both Worlds: Combining Recent Advances in Neural Machine
Translation},
pages = {76--86},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1906-00532,
author = {Aishwarya Bhandare and
Vamsi Sripathi and
Deepthi Karkada and
Vivek Menon and
Sun Choi and
Kushal Datta and
Vikram Saletore},
title = {Efficient 8-Bit Quantization of Transformer Neural Machine Language
Translation Model},
publisher = {CoRR},
volume = {abs/1906.00532},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/JacobKCZTHAK18,
author = {Benoit Jacob and
Skirmantas Kligys and
...
...
@@ -8239,14 +7545,6 @@ author = {Zhuang Liu and
volume = {abs/1611.08562},
year = {2016}
}
@inproceedings{xiao2013bagging,
title ={Bagging and boosting statistical machine translation systems},
author ={Tong Xiao and Jingbo Zhu and Tongran Liu },
publisher ={Artificial Intelligence},
volume ={195},
pages ={496--527},
year ={2013}
}
@inproceedings{DBLP:conf/emnlp/TrombleKOM08,
author = {Roy Tromble and
Shankar Kumar and
...
...
@@ -8270,29 +7568,6 @@ author = {Zhuang Liu and
pages = {3302--3308},
year = {2017}
}
@inproceedings{Shaw2018SelfAttentionWR,
author = {Peter Shaw and
Jakob Uszkoreit and
Ashish Vaswani},
title = {Self-Attention with Relative Position Representations},
publisher = {Proceedings of the Human Language Technology Conference of
the North American Chapter of the Association for Computational Linguistics},
pages = {464--468},
year = {2018}
}
@inproceedings{WangLearning,
author = {Qiang Wang and
Bei Li and
Tong Xiao and
Jingbo Zhu and
Changliang Li and
Derek F. Wong and
Lidia S. Chao},
title = {Learning Deep Transformer Models for Machine Translation},
pages = {1810--1822},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/FanGJ20,
author = {Angela Fan and
Edouard Grave and
...
...
@@ -8409,25 +7684,6 @@ author = {Zhuang Liu and
volume = {abs/2010.02416},
year = {2020}
}
@inproceedings{Vaswani2018Tensor2TensorFN,
author = {Ashish Vaswani and
Samy Bengio and
Eugene Brevdo and
Fran{\c{c}}ois Chollet and
Aidan N. Gomez and
Stephan Gouws and
Llion Jones and
Lukasz Kaiser and
Nal Kalchbrenner and
Niki Parmar and
Ryan Sepassi and
Noam Shazeer and
Jakob Uszkoreit},
title = {Tensor2Tensor for Neural Machine Translation},
pages = {193--199},
publisher = {Association for Machine Translation in the Americas},
year = {2018}
}
@inproceedings{Sun2019BaiduNM,
title={Baidu Neural Machine Translation Systems for WMT19},
author = {Meng Sun and
...
...
@@ -8610,17 +7866,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{KleinOpenNMT,
author = {Guillaume Klein and
Yoon Kim and
Yuntian Deng and
Jean Senellart and
Alexander M. Rush},
title = {OpenNMT: Open-Source Toolkit for Neural Machine Translation},
pages = {67--72},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/acl/WuWXTGQLL19,
author = {Lijun Wu and
Yiren Wang and
...
...
@@ -8635,16 +7880,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/HuangLMW17,
author = {Gao Huang and
Zhuang Liu and
Laurens van der Maaten and
Kilian Q. Weinberger},
title = {Densely Connected Convolutional Networks},
pages = {2261--2269},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{DBLP:journals/corr/GreffSS16,
author = {Klaus Greff and
Rupesh Kumar Srivastava and
...
...
@@ -8653,31 +7888,6 @@ author = {Zhuang Liu and
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{Bapna2018TrainingDN,
author = {Ankur Bapna and
Mia Xu Chen and
Orhan Firat and
Yuan Cao and
Yonghui Wu},
title = {Training Deeper Neural Machine Translation Models with Transparent
Attention},
pages = {3028--3033},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{WangLearning,
author = {Qiang Wang and
Bei Li and
Tong Xiao and
Jingbo Zhu and
Changliang Li and
Derek F. Wong and
Lidia S. Chao},
title = {Learning Deep Transformer Models for Machine Translation},
pages = {1810--1822},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2002-04745,
author = {Ruibin Xiong and
Yunchang Yang and
...
...
@@ -8705,86 +7915,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016},
}
@inproceedings{Ba2016LayerN,
author = {Lei Jimmy Ba and
Jamie Ryan Kiros and
Geoffrey E. Hinton},
title = {Layer Normalization},
publisher = {CoRR},
volume = {abs/1607.06450},
year = {2016}
}
@inproceedings{Vaswani2018Tensor2TensorFN,
author = {Ashish Vaswani and
Samy Bengio and
Eugene Brevdo and
Fran{\c{c}}ois Chollet and
Aidan N. Gomez and
Stephan Gouws and
Llion Jones and
Lukasz Kaiser and
Nal Kalchbrenner and
Niki Parmar and
Ryan Sepassi and
Noam Shazeer and
Jakob Uszkoreit},
title = {Tensor2Tensor for Neural Machine Translation},
pages = {193--199},
publisher = {Association for Machine Translation in the Americas},
year = {2018}
}
@inproceedings{Dou2019DynamicLA,
author = {Zi-Yi Dou and
Zhaopeng Tu and
Xing Wang and
Longyue Wang and
Shuming Shi and
Tong Zhang},
title = {Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement},
pages = {86--93},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2019}
}
@inproceedings{Wang2018MultilayerRF,
title={Multi-layer Representation Fusion for Neural Machine Translation},
author={Qiang Wang and Fuxue Li and Tong Xiao and Yanyang Li and Yinqiao Li and Jingbo Zhu},
publisher={International Conference on Computational Linguistics},
year={2018},
volume={abs/2002.06714}
}
@inproceedings{Dou2018ExploitingDR,
author = {Zi-Yi Dou and
Zhaopeng Tu and
Xing Wang and
Shuming Shi and
Tong Zhang},
title = {Exploiting Deep Representations for Neural Machine Translation},
pages = {4253--4262},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/LinFSYXZB17,
author = {Zhouhan Lin and
Minwei Feng and
C{\'{\i}}cero Nogueira dos Santos and
Mo Yu and
Bing Xiang and
Bowen Zhou and
Yoshua Bengio},
title = {A Structured Self-Attentive Sentence Embedding},
publisher = {International Conference on Learning Representations},
year = {2017},
}
@inproceedings{DBLP:conf/nips/SrivastavaGS15,
author = {Rupesh Kumar Srivastava and
Klaus Greff and
...
...
@@ -8830,15 +7960,6 @@ author = {Zhuang Liu and
pages = {1675--1685},
year = {2019}
}
@inproceedings{pmlr-v9-glorot10a,
author = {Xavier Glorot and
Yoshua Bengio},
title = {Understanding the difficulty of training deep feedforward neural networks},
publisher = {International Conference on Artificial Intelligence and Statistics},
volume = {9},
pages = {249--256},
year = {2010}
}
@inproceedings{DBLP:conf/iccv/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
...
...
@@ -9269,13 +8390,6 @@ author = {Zhuang Liu and
volume = {abs/2003.03384},
year = {2020}
}
@inproceedings{Chollet2017XceptionDL,
title={Xception: Deep Learning with Depthwise Separable Convolutions},
author = {Fran{\c{c}}ois Chollet},
publisher={IEEE Conference on Computer Vision and Pattern Recognition},
year={2017},
pages={1800-1807}
}
@inproceedings{DBLP:journals/tnn/AngelineSP94,
author = {Peter J. Angeline and
Gregory M. Saunders and
...
...
@@ -9523,20 +8637,6 @@ author = {Zhuang Liu and
volume = {abs/2009.02070},
year = {2020}
}
@inproceedings{DBLP:conf/acl/WangWLCZGH20,
author = {Hanrui Wang and
Zhanghao Wu and
Zhijian Liu and
Han Cai and
Ligeng Zhu and
Chuang Gan and
Song Han},
title = {{HAT:} Hardware-Aware Transformers for Efficient Natural Language
Processing},
pages = {7675--7688},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2008-06808,
author = {Henry Tsai and
Jayden Ooi and
...
...
@@ -9549,24 +8649,6 @@ author = {Zhuang Liu and
volume = {abs/2008.06808},
year = {2020}
}
@inproceedings{Wang2019ExploitingSC,
title={Exploiting Sentential Context for Neural Machine Translation},
author={Xing Wang and Zhaopeng Tu and Longyue Wang and Shuming Shi},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2019}
}
@inproceedings{Wei2020MultiscaleCD,
title={Multiscale Collaborative Deep Models for Neural Machine Translation},
author={Xiangpeng Wei and Heng Yu and Yue Hu and Yue Zhang and Rongxiang Weng and Weihua Luo},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2020}
}
@inproceedings{li2020shallow,
title={Shallow-to-Deep Training for Neural Machine Translation},
author={Li, Bei and Wang, Ziyang and Liu, Hui and Jiang, Yufan and Du, Quan and Xiao, Tong and Wang, Huizhen and Zhu, Jingbo},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2020}
}
@inproceedings{DBLP:journals/corr/abs-2007-06257,
author = {Hongfei Xu and
Qiuhui Liu and
...
...
@@ -9588,18 +8670,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2006-10369,
author = {Jungo Kasai and
Nikolaos Pappas and
Hao Peng and
James Cross and
Noah A. Smith},
title = {Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff
in Machine Translation},
publisher = {CoRR},
volume = {abs/2006.10369},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-1806-01261,
author = {Peter W. Battaglia and
Jessica B. Hamrick and
...
...
@@ -9633,34 +8703,6 @@ author = {Zhuang Liu and
volume = {abs/1806.01261},
year = {2018}
}
@inproceedings{Shaw2018SelfAttentionWR,
author = {Peter Shaw and
Jakob Uszkoreit and
Ashish Vaswani},
title = {Self-Attention with Relative Position Representations},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
pages = {464--468},
year = {2018},
}
@inproceedings{Dai2019TransformerXLAL,
author = {Zihang Dai and
Zhilin Yang and
Yiming Yang and
Jaime G. Carbonell and
Quoc V. Le and
Ruslan Salakhutdinov},
title = {Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {2978--2988},
year = {2019}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{DBLP:conf/acl/LiXTZZZ17,
author = {Junhui Li and
Deyi Xiong and
...
...
@@ -9681,18 +8723,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Yang2017TowardsBH,
author = {Baosong Yang and
Derek F. Wong and
Tong Xiao and
Lidia S. Chao and
Jingbo Zhu},
title = {Towards Bidirectional Hierarchical Representations for Attention-based
Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1432--1441},
year = {2017}
}
@inproceedings{DBLP:conf/acl/ChenHCC17,
author = {Huadong Chen and
Shujian Huang and
...
...
@@ -9704,16 +8734,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{TuModeling,
author = {Zhaopeng Tu and
Zhengdong Lu and
Yang Liu and
Xiaohua Liu and
Hang Li},
title = {Modeling Coverage for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/SennrichH16,
author = {Rico Sennrich and
Barry Haddow},
...
...
@@ -9739,13 +8759,6 @@ author = {Zhuang Liu and
publisher = {Annual Meeting of the Association for Computational Linguistics},
