DEMETR: Diagnosing Evaluation Metrics for Translation.
Marzena KarpinskaNishant RajKatherine ThaiYixiao SongAnkita GuptaMohit IyyerPublished in: EMNLP (2022)
Keyphrases
- evaluation metrics
- precision and recall
- average precision
- machine translation
- evaluation methods
- learning to rank
- evaluation measures
- evaluation framework
- statistical machine translation
- cross language information retrieval
- query translation
- data sets
- machine learning
- natural language processing
- machine translation system