Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level.
Daniel DeutschJuraj JuraskaMara FinkelsteinMarkus FreitagPublished in: CoRR (2023)
Keyphrases
- lexical cohesion
- evaluation metrics
- machine translation
- document level
- precision and recall
- sentiment classification
- language model
- average precision
- word level
- information extraction
- natural language processing
- language independent
- cross lingual
- query expansion
- sentence level
- pseudo relevance feedback
- target language
- evaluation measures
- cross language information retrieval
- data mining
- learning to rank
- question answering
- supervised learning
- natural language
- training data
- sentiment analysis
- query translation
- document retrieval
- coreference resolution
- training set
- machine translation system