FactRunner: A New System for NLP-Based Information Extraction from Wikipedia.
Rhio SutoyoChristoph QuixFisnik KastratiPublished in: WEBIST (Selected Papers) (2013)
Keyphrases
- information extraction
- named entities
- natural language processing
- wordnet
- natural language text
- named entity recognition
- computing semantic relatedness
- question answering
- free text
- semantic relations
- text mining
- precision and recall
- relation extraction
- semi structured
- named entity disambiguation
- structured data
- machine translation
- knowledge base
- text documents
- conditional random fields
- entity extraction
- machine learning
- word sense disambiguation
- web documents
- textual data
- text processing
- information retrieval
- language processing
- text analysis
- natural language
- entity ranking
- relational learning
- web mining
- computational linguistics
- wikipedia articles
- knowledge resources
- lexical resources
- semantic information
- world knowledge
- open domain
- document collections