2021

Simultaneous Multi-Pivot Neural Machine Translation

Dabre, Raj, Imankulova, Aizhan, Kaneko, Masahiro et al.

Understand

Parallel corpora are indispensable for training neural machine translation (NMT) models, and parallel corpora for most language pairs do not exist or are scarce.

In such cases, pivot language NMT can be helpful where a pivot language is used such that there exist parallel corpora between the source and pivot and pivot and target languages.
Naturally, the quality of pivot language translation is more inferior to what could be achieved with a direct parallel corpus of a reasonable size for that pair.
In a real-time simultaneous translation setting, the quality of pivot language translation deteriorates even further given that the model has to output translations the moment a few source words become available.

Built on

BLEU: a method for automatic evaluation of machine translation
Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002 · 2002
Earlier work this paper cites.
A comparison of pivot methods for phrase-based statistical machine translation
Masao Utiyama and Hitoshi Isahara. 2007 · 2007
Earlier work this paper cites.
Pivot language approach for phrase-based statistical machine translation
Hua Wu and Haifeng Wang. 2007 · 2007
Earlier work this paper cites.
Phrase-based statistical machine translation with pivot languages
N. Bertoldi, M. Barbaiani, M. Federico, and R. Cattoni. 2008 · 2008
Earlier work this paper cites.
Neural machine translation by jointly learning to align and translate
Original
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015 · 2015
Earlier work this paper cites.
Leveraging small multilingual corpora for SMT using many pivot languages
Raj Dabre, Fabien Cromieres, Sadao Kurohashi, and Pushpak Bhattacharyya. 2015 · 2015
Earlier work this paper cites.
Can neural machine translation do simultaneous translation?
Original
Kyunghyun Cho and Masha Esipova. 2016 · 2016
Earlier work this paper cites.
Zero-resource translation with multi-lingual neural machine translation
Orhan Firat, Baskaran Sankaran, Yaser Al-Onaizan, Fatos T. Yarman Vural, and Kyunghyun Cho. 2016 · 2016
Earlier work this paper cites.
Ensemble learning for multi-source neural machine translation
Ekaterina Garmash and Christof Monz. 2016 · 2016
Earlier work this paper cites.

Similar

Improving neural machine translation models with monolingual data
Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016 · 2016
Cited alongside, same era.
Multi-source neural translation
Original
Barret Zoph and Kevin Knight. 2016 · 2016
Cited alongside, same era.
Joint training for pivot-based neural machine translation
Yong Cheng, Qian Yang, Yang Liu, Maosong Sun, and Wei Xu. 2017 · 2017
Cited alongside, same era.
Enabling multi-source neural machine translation by concatenating source sentences in multiple languages
Raj Dabre, Fabien Cromieres, and Sadao Kurohashi. 2017 · 2017
Cited alongside, same era.
Learning to translate in real-time with neural machine translation
Jiatao Gu, Graham Neubig, Kyunghyun Cho, and Victor OK Li. 2017 · 2017
Cited alongside, same era.
Google’s multilingual neural machine translation system: Enabling zero-shot translation
Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2017 · 2017
Cited alongside, same era.
Multi-source syntactic neural machine translation
Anna Currey and Kenneth Heafield. 2018 · 2018
Cited alongside, same era.
Incremental decoding and training methods for simultaneous translation in neural machine translation
Fahim Dalvi, Nadir Durrani, Hassan Sajjad, and Stephan Vogel. 2018 · 2018
Cited alongside, same era.
Multi-source neural machine translation with missing data
Yuta Nishimura, Katsuhito Sudoh, Graham Neubig, and Satoshi Nakamura. 2018 · 2018
Cited alongside, same era.
Simultaneous translation with flexible policy via restricted imitation learning
Baigong Zheng, Renjie Zheng, Mingbo Ma, and Liang Huang. 2019b
Cited in the paper.

Then

Zero-resource neural machine translation with monolingual pivot data
Anna Currey and Kenneth Heafield. 2019 · 2019
Later among the works it cites.
Improved zero-shot neural machine translation via ignoring spurious correlations
Jiatao Gu, Yong Wang, Kyunghyun Cho, and Victor O.K. Li. 2019 · 2019
Later among the works it cites.
STACL: Simultaneous translation with implicit anticipation and controllable latency using prefix-to-prefix framework
Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, and Haifeng Wang. 2019 · 2019
Later among the works it cites.
Simpler and faster learning of adaptive policies for simultaneous translation
Baigong Zheng, Renjie Zheng, Mingbo Ma, and Liang Huang. 2019a · 2019
Later among the works it cites.
Speculative beam search for simultaneous translation
Renjie Zheng, Mingbo Ma, Baigong Zheng, and Liang Huang. 2019c · 2019
Later among the works it cites.
Simultaneous machine translation with visual context
Ozan Caglayan, Julia Ive, Veneta Haralampieva, Pranava Madhyastha, Loïc Barrault, and Lucia Specia. 2020 · 2020
Later among the works it cites.
Towards multimodal simultaneous neural machine translation
Aizhan Imankulova, Masahiro Kaneko, Tosho Hirasawa, and Mamoru Komachi. 2020 · 2020
Later among the works it cites.
Improving massively multilingual neural machine translation and zero-shot translation
Biao Zhang, Philip Williams, Ivan Titov, and Rico Sennrich. 2020 · 2020
Later among the works it cites.
Opportunistic decoding with timely correction for simultaneous translation
Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, and Liang Huang. 2020 · 2020
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…