publication . Conference object . Preprint . 2019

Consistency by Agreement in Zero-Shot Neural Machine Translation

Maruan Al-Shedivat; Ankur P. Parikh;
Open Access
  • Published: 03 Apr 2019
  • Publisher: Association for Computational Linguistics
Abstract
Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests models on translation directions they have not been optimized for at training time. To solve the problem, we (i) reformulate multilingual translation as probabilistic inference, (ii) define the notion of zero-shot consistency and show why standard training often results in models unsuitable for zero-shot tasks, and (iii) introduce a consistent agreement-based training method that encourages the model to produce equivalent tra...
Persistent Identifiers
Subjects
free text keywords: Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning, Artificial intelligence, business.industry, business, Computer science, Natural language processing, computer.software_genre, computer, Probabilistic inference, Training time, Training methods, Machine translation
Related Organizations
Communities
Digital Humanities and Cultural Heritage
54 references, page 1 of 4

Mart´ın Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. Tensorflow: a system for large-scale machine learning. In OSDI, volume 16, pages 265- 283.

Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E Dahl, and Geoffrey E Hinton. 2018. Large scale distributed neural network training through online distillation. arXiv preprint arXiv:1804.03235.

Naveen Arivazhagan, Ankur Bapna, Orhan Firat, Roee Aharoni, Melvin Johnson, and Wolfgang Macherey. 2018. The missing ingredient in zero-shot neural machine translation. OpenReview.net.

Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2017. Unsupervised neural machine translation. arXiv preprint arXiv:1710.11041.

Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.

Orhan Firat, Kyunghyun Cho, and Yoshua Bengio. 2016a. Multi-way, multilingual neural machine translation with a shared attention mechanism. arXiv preprint arXiv:1601.01073.

Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan. 2010. A theory of learning from different domains. Machine learning, 79(1-2):151-175.

Julian Besag. 1975. Statistical analysis of non-lattice data. The statistician, pages 179-195.

Ondrej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Varvara Logacheva, Christof Monz, et al. 2016. Findings of the 2016 conference on machine translation. In ACL 2016 FIRST CONFERENCE ON MACHINE TRANSLATION (WMT16), pages 131-198. The Association for Computational Linguistics.

Yun Chen, Yang Liu, Yong Cheng, and Victor OK Li. 2017. A teacher-student framework for zeroresource neural machine translation. arXiv preprint arXiv:1705.00753.

Yong Cheng, Qian Yang, Yang Liu, Maosong Sun, and Wei Xu. 2017. Joint training for pivot-based neural machine translation. In Proceedings of IJCAI.

Kyunghyun Cho, Bart Van Merrie¨nboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.

Trevor Cohn and Mirella Lapata. 2007. Machine translation by triangulation: Making effective use of multi-parallel corpora. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 728-735. [OpenAIRE]

Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, and Herve´ Je´gou. 2017. Word translation without parallel data. arXiv preprint arXiv:1710.04087.

Alexis Conneau, Guillaume Lample, Ruty Rinott, Adina Williams, Samuel R Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. Xnli: Evaluating crosslingual sentence representations. arXiv preprint arXiv:1809.05053.

54 references, page 1 of 4
Any information missing or wrong?Report an Issue