Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents with Semantic-Oriented Hierarchical Graphs.
Fengbin ZhuChao WangFuli FengZifeng RenMoxin LiTat-Seng ChuaPublished in: CoRR (2023)
Keyphrases
- text documents
- text mining
- text representation
- text classification
- information extraction
- keywords
- wordnet
- text categorization
- topic models
- semantic information
- bag of words
- document clustering
- semantic features
- natural language
- semantic similarity
- semantically rich
- named entities
- feature selection
- database
- databases
- structured data
- domain specific
- co occurrence
- domain ontology
- unsupervised learning
- natural language processing
- data analysis
- knowledge base
- artificial intelligence
- relevant concepts