1. Paper title
Boosting Neural Machine Translation with Similar Translations
2. link
https://www.aclweb.org/anthology/2020.acl-main.144.pdf
3. 摘要
This paper explores data augmentation methods for training Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches. In particular, we show how we can simply feed the neural model with information on both source and target sides of the fuzzy matches, we also extend the similarity to include semantically related translations retrieved using distributed sentence representations. We show that translations based on fuzzy matching provide the model with “copy” information while translations based on embedding similarities tend to extend the translation “context”. Results indicate that the effect from both similar sentences are adding up to further boost accuracy, are combining naturally with model fine-tuning and are providing dynamic adaptation for unseen translation pairs. Tests on multiple data sets and domains show consistent accuracy improvements. To foster research around these techniques, we also release an Open-Source toolkit with efficient and flexible fuzzy-match implementation.
fuzzy matches:模糊匹配
[?] similar translations
4. 要解决什么问题
NMT中的数据增加技术。
5. 作者的主要贡献
使用源和目标的模糊匹配作为NMT的训练数据
[?] 没看懂
使用基于分布句子表示的语义相关翻译作为NMT的训练数据
6. 得到了什么结果
模糊匹配的数据为NMT提供“copy”信息
[?] 没看懂
embedding相似性能NMT提供"context"
增加模糊匹配的数据来训练NMT可以提高性能。