Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment.
Yongxin HuangKexin WangGoran GlavasIryna GurevychPublished in: CoRR (2024)
Keyphrases
- parallel corpus
- cross lingual
- word alignment
- machine translation
- source language
- target language
- word level
- european languages
- natural language
- language independent
- language specific
- cross lingual information retrieval
- event extraction
- cross language
- query translation
- language modeling
- machine translation system
- indian languages
- text classification
- linguistic resources
- sentiment classification
- translation model
- comparable corpora
- statistical machine translation
- cross language information retrieval
- news articles
- parallel corpora
- information retrieval
- information extraction
- document clustering
- word sense