TBL-Improved Non-Deterministic Segmentation and POS Tagging for a Chinese Parser.
Martin ForstJi FangPublished in: EACL (2009)
Keyphrases
- word segmentation
- pos tagging
- chinese word segmentation
- penn treebank
- dependency parsing
- pos taggers
- part of speech
- n gram
- text classification
- natural language processing
- document analysis
- language independent
- language modeling
- natural language
- transformation based learning
- cross lingual
- out of vocabulary
- machine translation
- maximum entropy
- text mining