Chinese Unknown Words Extraction Based on Word-Level Characteristics.
Wenbo PangXiaozhong FanYijun GuJiangde YuPublished in: HIS (1) (2009)
Keyphrases
- word segmentation
- unknown words
- word level
- n gram
- language independent
- word recognition
- morphological analysis
- document analysis
- text classification
- language modeling
- word sense
- document images
- cross lingual
- part of speech
- information extraction
- knowledge representation
- machine learning
- word sense disambiguation
- co occurrence
- natural language processing
- information retrieval