Word Segmentation for the Sequences Emitted from a Word-Valued Source.
Takashi IshidaToshiyasu MatsushimaShigeichi HirasawaPublished in: CIT (2007)
Keyphrases
- word segmentation
- word recognition
- n gram
- chinese word segmentation
- handwriting recognition
- pos tagging
- chinese text
- chinese text retrieval
- unknown words
- language independent
- text classification
- hidden markov models
- word level
- language modeling
- document analysis
- pattern recognition
- data mining
- sparse data
- part of speech
- query expansion
- statistical language modeling