Multi-layered summarization of spoken document archives by information extraction and semantic structuring.
Lin-Shan LeeSheng-yi KongYi-Cheng PanYi-Sheng FuYu-tsun HuangPublished in: INTERSPEECH (2006)
Keyphrases
- multi layered
- information extraction
- document archives
- text summarization
- neural learning
- natural language
- precision and recall
- natural language processing
- information retrieval
- semantic annotation
- semantic tagging
- unstructured documents
- semantic web
- named entities
- named entity recognition
- linguistic patterns
- natural language text
- document collections
- soccer video
- sports video
- text mining
- machine learning
- free text
- question answering
- relation extraction
- semantic search
- structured data
- semi structured
- semantic network
- web documents
- high level
- semantic knowledge
- web mining
- semantic similarity
- video summarization
- semantic information
- relational learning
- video data
- speech recognition