Extrapolating Large Language Models to Non-English by Aligning Languages.
Wenhao ZhuYunzhe LvQingxiu DongFei YuanJingjing XuShujian HuangLingpeng KongJiajun ChenLei LiPublished in: CoRR (2023)
Keyphrases
- term dependencies
- language model
- statistical machine translation
- language modeling
- cross lingual
- comparable corpora
- n gram
- language independent
- target language
- translation model
- cross language retrieval
- retrieval model
- query translation
- probabilistic model
- cross language
- query expansion
- document retrieval
- information retrieval
- machine translation
- machine translation system
- speech recognition
- language modelling
- query terms
- parallel corpora
- context sensitive
- test collection
- multiword
- bilingual dictionaries
- ad hoc information retrieval
- indian languages
- chinese english
- source language
- relevance model
- smoothing methods
- statistical language models
- vector space model
- cross language information retrieval
- word level
- statistical language modeling
- language models for information retrieval
- retrieval effectiveness
- natural language