Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation.
Mengge LiuWen ZhangXiang LiJian LuanBin WangYuhang GuoShuoying ChenPublished in: CoRR (2023)
Keyphrases
- test set
- machine translation
- error rate
- training set
- language processing
- language independent
- natural language processing
- information extraction
- cross lingual
- target language
- training data
- natural language
- cross language information retrieval
- natural language generation
- test data
- word sense disambiguation
- language resources
- statistical machine translation
- word level
- artificial intelligence
- word alignment
- multilingual documents
- chinese english
- machine transliteration
- brazilian portuguese
- parallel corpus
- precision and recall
- feature extraction