Collecting sentences from web resources for constructing spontaneous Chinese language model.
Xinhui HuYouzheng WuShigeki MatsudaChiori HoriHideki KashiokaPublished in: ISCSLP (2012)
Keyphrases
- language model
- web resources
- text summarization
- language modeling
- language modeling approaches
- n gram
- query expansion
- probabilistic model
- speech recognition
- dependency structure
- sentence retrieval
- word segmentation
- document level
- learning resources
- information retrieval
- document retrieval
- retrieval model
- mixture model
- natural language
- multiword
- context sensitive
- web content
- test collection
- ad hoc information retrieval
- smoothing methods
- chinese english
- web pages
- translation model
- statistical machine translation
- learning objects
- cross lingual
- learning styles
- information extraction
- social tagging
- query specific
- machine learning