BigTrans: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages.
Wen YangChong LiJiajun ZhangChengqing ZongPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- cross lingual
- comparable corpora
- translation model
- statistical machine translation
- cross lingual information retrieval
- language resources
- machine translation system
- cross language
- language independent
- parallel corpus
- parallel corpora
- query translation
- bilingual dictionaries
- n gram
- document retrieval
- probabilistic model
- cross language information retrieval
- chinese english
- machine translation
- cross language retrieval
- retrieval model
- query expansion
- information retrieval
- query terms
- speech recognition
- linguistic resources
- out of vocabulary
- test collection
- language modelling
- target language
- vector space model
- context sensitive
- multiword
- relevance model
- language models for information retrieval
- multilingual retrieval
- statistical language models
- word level
- source language
- information extraction
- bayesian networks
- ad hoc information retrieval
- language model for information retrieval
- statistical language modeling
- okapi bm
- indian languages
- text classification
- search engine