|
| | | | |
| | | |
| Stat |
Members: 3645
Articles: 2'504'928
Articles rated: 2609
26 April 2024 |
|
| | | | |
|
Article overview
| |
|
|
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations | | Jiatao Gu
; Yong Wang
; Kyunghyun Cho
; Victor O.K. Li
; | | Date: |
4 Jun 2019 | | Abstract: | Zero-shot translation, translating between language pairs on which a Neural
Machine Translation (NMT) system has never been trained, is an emergent
property when training the system in multilingual settings. However, naive
training for zero-shot NMT easily fails, and is sensitive to hyper-parameter
setting. The performance typically lags far behind the more conventional
pivot-based approach which translates twice using a third language as a pivot.
In this work, we address the degeneracy problem due to capturing spurious
correlations by quantitatively analyzing the mutual information between
language IDs of the source and decoded sentences. Inspired by this analysis, we
propose to use two simple but effective approaches: (1) decoder pre-training;
(2) back-translation. These methods show significant improvement (4~22 BLEU
points) over the vanilla zero-shot translation on three challenging
multilingual datasets, and achieve similar or better results than the
pivot-based approach. | | Source: | arXiv, 1906.1181 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
|
News, job offers and information for researchers and scientists:
| |
REGISTER