When printed hypertexts go digital: information extraction from the parsing of indices.
Matteo RomanelloMonica BertiAlison BabeuGregory R. CranePublished in: Hypertext (2009)
Keyphrases
- information extraction
- natural language processing
- natural language
- digital documents
- free text
- text mining
- web mining
- machine learning
- intermediate representation
- text summarization
- precision and recall
- question answering
- named entities
- structured data
- web documents
- relational learning
- text processing
- semi structured
- open domain
- textual data
- information retrieval
- relation extraction
- data sets
- linguistic analysis
- data extraction
- context free grammars
- barcode
- digital media
- probabilistic model
- named entity recognition
- word sense disambiguation
- machine translation