Vocabulary Learning via Optimal Transport for Neural Machine Translation

Jingjing Xu, Hao Zhou, Chun Gan, Zaixiang Zheng, Lei Li


Abstract
The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether we can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of vocabulary from the perspective of information theory. It motivates us to formulate the quest of vocabularization – finding the best token dictionary with a proper size – as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation. For example, VOLT achieves 70% vocabulary size reduction and 0.5 BLEU gain on English-German translation. Also, compared to BPE-search, VOLT reduces the search time from 384 GPU hours to 30 GPU hours on English-German translation. Codes are available at https://github.com/Jingjing-NLP/VOLT.
Anthology ID:
2021.acl-long.571
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7361–7373
Language:
URL:
https://aclanthology.org/2021.acl-long.571
DOI:
10.18653/v1/2021.acl-long.571
Award:
 Best Paper
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.571.pdf
Code
 Jingjing-NLP/VOLT