Consideration of the Word's Neighborhood in GATs for Information Extraction in Semi-structured Documents.
Djedjiga BelhadjYolande BelaïdAbdel BelaïdPublished in: ICDAR (2) (2021)
Keyphrases
- semi structured documents
- information extraction
- free text
- semi structured
- natural language text
- word sense disambiguation
- structured data
- natural language processing
- text mining
- web documents
- text documents
- textual data
- named entity recognition
- named entities
- question answering
- machine learning
- n gram
- co occurrence
- information retrieval
- word segmentation
- precision and recall
- data extraction
- natural language
- text processing
- relational learning
- keywords
- word pairs
- conditional random fields
- xml schema
- domain specific
- xml documents
- word recognition
- web mining
- databases
- ontology based information extraction