Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs.
Fengbin ZhuChao WangFuli FengZifeng RenMoxin LiTat-Seng ChuaPublished in: LREC/COLING (2024)
Keyphrases
- text documents
- text mining
- text representation
- text classification
- wordnet
- text categorization
- information extraction
- keywords
- topic models
- semantic similarity
- document clustering
- semantic features
- semantically rich
- knowledge base
- semantic information
- bag of words
- named entities
- natural language
- relevant concepts
- data mining
- database
- concept hierarchy
- semantic knowledge
- domain specific
- semantic relations
- natural language processing
- machine learning
- unsupervised learning
- high dimensional
- information extraction systems