Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling.
Zhijun WangXuebo LiuMin ZhangPublished in: EMNLP (2022)
Keyphrases
- chinese characters
- machine translation
- chinese character recognition
- character recognition
- language independent
- cross lingual
- information extraction
- language processing
- word level
- machine translation system
- natural language generation
- language resources
- cross language information retrieval
- natural language processing
- statistical machine translation
- natural language
- target language
- word sense disambiguation
- word alignment
- brazilian portuguese
- chinese english
- query translation
- machine learning
- text categorization
- data mining
- parallel corpora
- parallel corpus
- tasks in natural language processing