Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models: A Case Study on ChatGPT.
Qingyu LuBaopu QiuLiang DingLiping XieDacheng TaoPublished in: CoRR (2023)
Keyphrases
- language model
- error analysis
- translation model
- language modeling
- cross language retrieval
- document retrieval
- probabilistic model
- least squares
- n gram
- speech recognition
- language modelling
- retrieval model
- statistical language models
- context sensitive
- ad hoc information retrieval
- query expansion
- out of vocabulary
- information retrieval
- query translation
- test collection
- document ranking
- query terms
- smoothing methods
- cross language
- error correction
- passage retrieval
- information retrieval systems
- optical flow
- search engine