2020

Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation

Peng, Wei, Huang, Chongxuan, Li, Tianhao et al.

Understand

Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora.

These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology.
This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT.
DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus.

Built on

Semi-supervised learning for neural machine translation
Yong Cheng, Wei Xu, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu. 2016 · 1974
Earlier work this paper cites.
Moses: Open source toolkit for statistical machine translation
Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. 2007 · 2007
Earlier work this paper cites.
A simple, fast, and effective reparameterization of IBM model 2
Chris Dyer, Victor Chahuneau, and Noah A. Smith. 2013 · 2013
Earlier work this paper cites.
Normalized word embedding and orthogonal transform for bilingual word translation
Chao Xing, Dong Wang, Chao Liu, and Yiye Lin. 2015 · 2015
Earlier work this paper cites.
Exploiting source-side monolingual data in neural machine translation
Jiajun Zhang and Chengqing Zong. 2016b · 2016
Earlier work this paper cites.
Translating domain-specific expressions in knowledge bases with neural machine translation
Original
Mihael Arcan and Paul Buitelaar. 2017 · 2017
Earlier work this paper cites.
Copied monolingual data improves low-resource neural machine translation
Anna Currey, Antonio Valerio Miceli Barone, and Kenneth Heafield. 2017 · 2017
Earlier work this paper cites.
Using target-side monolingual data for neural machine translation through multi-task learning
Tobias Domhan and Felix Hieber. 2017 · 2017
Earlier work this paper cites.

Similar

Data augmentation for low-resource neural machine translation
Marzieh Fadaee, Arianna Bisazza, and Christof Monz. 2017 · 2017
Cited alongside, same era.
Lexically constrained decoding for sequence generation using grid beam search
Chris Hokamp and Qun Liu. 2017 · 2017
Cited alongside, same era.
Billion-scale similarity search with gpus
Original
Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2017 · 2017
Cited alongside, same era.
Overcoming catastrophic forgetting in neural networks
James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell. 2017 · 2017
Cited alongside, same era.
Six challenges for neural machine translation
Philipp Koehn and Rebecca Knowles. 2017 · 2017
Cited alongside, same era.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017 · 2017
Cited alongside, same era.
Sentence embedding for neural machine translation domain adaptation
Rui Wang, Andrew Finch, Masao Utiyama, and Eiichiro Sumita. 2017 · 2017
Cited alongside, same era.
Dynamic data selection for neural machine translation
Marlies van der Wees, Arianna Bisazza, and Christof Monz. 2017 · 2017
Cited alongside, same era.
Improving neural machine translation models with monolingual data
Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016a
Cited in the paper.
Neural machine translation of rare words with subword units
Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016b
Cited in the paper.
Bridging neural machine translation and bilingual dictionaries
Original
Jiajun Zhang and Chengqing Zong. 2016a
Cited in the paper.

Then

A survey of domain adaptation for neural machine translation
Chenhui Chu and Rui Wang. 2018 · 2018
Later among the works it cites.
Bert: Pre-training of deep bidirectional transformers for language understanding
Original
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018 · 2018
Later among the works it cites.
Word translation without parallel data
Guillaume Lample, Alexis Conneau, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. 2018 · 2018
Later among the works it cites.
A call for clarity in reporting BLEU scores
Matt Post. 2018 · 2018
Later among the works it cites.
bert-as-service
Han Xiao. 2018 · 2018
Later among the works it cites.
Domain adaptation of neural machine translation by lexicon induction
Junjie Hu, Mengzhou Xia, Graham Neubig, and Jaime Carbonell. 2019 · 2019
Later among the works it cites.
fairseq: A fast, extensible toolkit for sequence modeling
Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019 · 2019
Later among the works it cites.
HABLex: Human annotated bilingual lexicons for experiments in machine translation
Brian Thompson, Rebecca Knowles, Xuan Zhang, Huda Khayrallah, Kevin Duh, and Philipp Koehn. 2019 · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…