When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?

Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs. Meanwhile, the contrastive objective can implicitly utilize auto...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-04
Main Authors: Mao, Zhuoyuan, Chu, Chenhui, Dabre, Raj, Song, Haiyue, Wan, Zhen, Kurohashi, Sadao
Format: Article
Language:English
Subjects:
Alignment
Coders
Empirical analysis
Machine translation
Retrieval
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs. Meanwhile, the contrastive objective can implicitly utilize automatically learned word alignment, which has not been explored in many-to-many NMT. This work proposes a word-level contrastive objective to leverage word alignments for many-to-many NMT. Empirical results show that this leads to 0.8 BLEU gains for several language pairs. Analyses reveal that in many-to-many NMT, the encoder's sentence retrieval performance highly correlates with the translation quality, which explains when the proposed method impacts translation. This motivates future exploration for many-to-many NMT to improve the encoder's sentence retrieval performance.
ISSN:2331-8422