Improving Information Extraction on Business Documents with Specific Pre-training Tasks.
Thibault DouzonStefan DuffnerChristophe GarciaJérémy EspinasPublished in: DAS (2022)
Keyphrases
- information extraction
- free text
- information retrieval
- web documents
- decision making
- information retrieval systems
- information systems
- textual data
- document collections
- named entity recognition
- text documents
- natural language processing
- data mining
- information extraction systems
- business models
- precision and recall
- semi structured
- business processes
- text mining
- machine learning
- business process
- document clustering
- natural language text
- document classification
- unstructured text
- training corpus
- relation extraction
- text classifiers
- keywords
- vector space model
- retrieval systems
- training examples
- business intelligence
- web mining