Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity.
Eric KhiuHasti ToossiDavid AnugrahaJinyu LiuJiaxu LiJuan Armando Parra FloresLeandro Acros RomanA. Seza DogruözEn-Shiun Annie LeePublished in: CoRR (2024)
Keyphrases
- machine translation
- language independent
- target language
- cross lingual
- statistical machine translation
- multilingual documents
- machine translation system
- language resources
- language specific
- parallel corpora
- information extraction
- source language
- query translation
- cross language information retrieval
- comparable corpora
- natural language processing
- language processing
- natural language generation
- bilingual dictionaries
- similarity measure
- grammar induction
- brazilian portuguese
- machine readable dictionaries
- natural language
- word alignment
- word pairs
- cross lingual information retrieval
- word order
- word sense disambiguation
- language modeling
- word level
- semantic similarity
- chinese english
- finite state transducers
- multilingual information retrieval
- edit distance
- parallel corpus
- linguistic resources
- text retrieval
- expert systems
- cross language
- cross domain
- domain dependent
- knowledge base