The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation.
Patrick FernandesDaniel DeutschMara FinkelsteinParker RileyAndré MartinsGraham NeubigAnkush GargJonathan H. ClarkMarkus FreitagOrhan FiratPublished in: WMT (2023)
Keyphrases
- fine grained
- language model
- machine translation
- statistical machine translation
- language modeling
- cross lingual
- n gram
- document retrieval
- access control
- probabilistic model
- natural language processing
- information extraction
- information retrieval
- query expansion
- target language
- speech recognition
- test collection
- language independent
- retrieval model
- natural language
- cross language information retrieval
- sentence retrieval
- context sensitive
- query terms
- ad hoc information retrieval
- relevance model
- chinese english
- out of vocabulary
- parallel corpora
- high level
- word level
- source language
- machine translation system
- vector space model
- xml retrieval
- pseudo relevance feedback
- query translation
- text retrieval
- text classification
- co occurrence
- web search