Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment.
Zhongtao MiaoQiyu WuKaiyan ZhaoZilong WuYoshimasa TsuruokaPublished in: CoRR (2024)
Keyphrases
- cross lingual
- word alignment
- parallel corpus
- machine translation
- language independent
- language modeling
- target language
- cross language
- statistical machine translation
- source language
- natural language
- translation model
- machine translation system
- text classification
- news articles
- transfer learning
- information extraction
- query translation
- pairwise
- parallel corpora
- word sense
- document clustering
- text summarization
- language model