A statistical approach for resolving problematical word boundaries in Chinese lexicography.
Oi Yee KwongBenjamin K. TsouPublished in: SMC (2001)
Keyphrases
- word segmentation
- chinese word segmentation
- chinese text
- statistical models
- statistical analysis
- unknown words
- information theoretic
- word recognition
- n gram
- co occurrence
- data driven
- word sense disambiguation
- english chinese
- english text
- probabilistic context free grammars
- keywords
- statistical approaches
- sentence level
- text summarization
- object boundaries
- language model