1 |
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? ...
|
|
|
|
Abstract:
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. ... : NAACL 2022 findings ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2204.12165 https://arxiv.org/abs/2204.12165
|
|
BASE
|
|
Hide details
|
|
2 |
VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Linguistically-driven Multi-task Pre-training for Low-resource Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Attending Self-Attention: A Case Study ofVisually Grounded Supervision in Vision-and-Language Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Lightweight Cross-Lingual Sentence Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A Corpus for English-Japanese Multimodal Neural Machine Translation with Comparable Sentences ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
A Comprehensive Survey of Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Lexically Cohesive Neural Machine Translation with Copy Mechanism ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
iParaphrasing: Extracting Visually Grounded Paraphrases via an Image ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|