Paraphrases as Foreign Languages in Multilingual Neural Machine Translation

Zhong Zhou, Matthias Sperber, Alexander Waibel


Abstract
Paraphrases, rewordings of the same semantic meaning, are useful for improving generalization and translation. Unlike previous works that only explore paraphrases at the word or phrase level, we use different translations of the whole training data that are consistent in structure as paraphrases at the corpus level. We treat paraphrases as foreign languages, tag source sentences with paraphrase labels, and train on parallel paraphrases in the style of multilingual Neural Machine Translation (NMT). Our multi-paraphrase NMT that trains only on two languages outperforms the multilingual baselines. Adding paraphrases improves the rare word translation and increases entropy and diversity in lexical choice. Adding the source paraphrases boosts performance better than adding the target ones, while adding both lifts performance further. We achieve a BLEU score of 57.2 for French-to-English translation using 24 corpus-level paraphrases of the Bible, which outperforms the multilingual baselines and is +34.7 above the single-source single-target NMT baseline.
Anthology ID:
P19-2015
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Fernando Alva-Manchego, Eunsol Choi, Daniel Khashabi
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
113–122
Language:
URL:
https://aclanthology.org/P19-2015
DOI:
10.18653/v1/P19-2015
Bibkey:
Cite (ACL):
Zhong Zhou, Matthias Sperber, and Alexander Waibel. 2019. Paraphrases as Foreign Languages in Multilingual Neural Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 113–122, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Paraphrases as Foreign Languages in Multilingual Neural Machine Translation (Zhou et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-2015.pdf