Abstract
Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality. The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training. We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. With this modification, we gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions. The improvements are particularly prominent between related languages, where our proposed model outperforms pivot-based translation. Moreover, our approach allows easy integration of new languages, which substantially expands translation coverage. By thorough inspections of the hidden layer outputs, we show that our approach indeed leads to more language-independent representations.
Original language | English |
---|---|
Title of host publication | 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) |
Publisher | Association for Computational Linguistics |
Pages | 1259–1273 |
Number of pages | 15 |
Volume | 1 |
Edition | August 2021 |
ISBN (Print) | 9781954085527 |
DOIs | |
Publication status | Published - 2021 |
Event | The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing - Online, Unknown Duration: 1 Aug 2021 → 6 Aug 2021 https://2021.aclweb.org/ |
Conference
Conference | The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing |
---|---|
Abbreviated title | ACL-IJCNLP 2021 |
Country/Territory | Unknown |
Period | 1/08/21 → 6/08/21 |
Internet address |