Multilingual Representation Distillation with Contrastive Learning

arxiv(2022)

引用 0|浏览62
暂无评分
摘要
Multilingual sentence representations from large models can encode semantic information from two or more languages and can be used for different cross-lingual information retrieval tasks. In this paper, we integrate contrastive learning into multilingual representation distillation and use it for quality estimation of parallel sentences (find semantically similar sentences that can be used as translations of each other). We validate our approach with multilingual similarity search and corpus filtering tasks. Experiments across different low-resource languages show that our method significantly outperforms previous sentence encoders such as LASER, LASER3, and LaBSE.
更多
查看译文
关键词
representation,learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要