Selecting on-topic sentences from natural language corpora.
Michael LevitElizabeth BoscheeMarjorie FreedmanPublished in: INTERSPEECH (2007)
Keyphrases
- natural language
- natural language processing
- topic segmentation
- word frequency
- syntactic structures
- text corpora
- multi document summarization
- highly ambiguous
- natural language sentences
- natural language interface
- automatic summarization
- knowledge representation
- text generation
- semantic analysis
- natural language generation
- dialogue system
- question answering
- machine learning
- linguistic analysis
- text corpus
- language processing
- information extraction
- text summarization
- text mining
- document set
- linguistic knowledge
- semantic interpretation
- natural language understanding
- semantic representation
- document corpus
- news articles
- question answering systems
- wordnet
- natural language text