Detecting Korean Hedge Sentences in Wikipedia Documents.
Sin-Jae KangJu-Seok JeongIn-Su KangPublished in: ICHIT (1) (2012)
Keyphrases
- hedge detection
- document collections
- text corpus
- sentence level
- sequence labeling
- document summarization
- multi document summarization
- document set
- wikipedia articles
- extractive summarization
- wikipedia pages
- document level
- document representation
- document clustering
- information retrieval
- automatic summarization
- information retrieval systems
- web documents
- natural language
- sentiment analysis
- text documents
- sentence similarity
- linguistic analysis
- metadata
- sentence extraction
- knowledge base
- text corpora
- natural language text
- semantic information
- document retrieval
- xml documents
- semantic relations
- retrieval systems
- multiword
- concept space
- conditional random fields
- word frequency
- automatic text summarization
- test collection
- summary generation
- named entities
- relevant documents
- keywords
- vector space model
- noun phrases
- machine translation system