Looking at words and points with attention: a benchmark for text-to-shape coherence.
Andrea AmaduzziGiuseppe LisantiSamuele SaltiLuigi Di StefanoPublished in: CoRR (2023)
Keyphrases
- text documents
- keywords
- english words
- text recognition
- medial axis
- text databases
- syntactic categories
- related words
- sample points
- chinese text
- text corpus
- proper nouns
- shape model
- word pairs
- multiword
- world knowledge
- n gram
- arbitrary shape
- text corpora
- point sets
- linguistic analysis
- salient points
- information extraction
- arabic text
- lexical features
- text mining
- stop words
- textual features
- text representation
- shape representation
- natural language text
- short text
- linguistic information
- data points
- boundary points
- polygonal approximation
- printed text
- shape features
- arabic language
- information retrieval
- text graphics
- punctuation marks
- word co occurrence
- co occurrence
- feature points
- noun phrases
- geodesic distance
- document representation
- word sense disambiguation
- text retrieval