Hybrid approach for text similarity detection in Vietnamese based on Sentence-BERT and WordNet.
Son CaoHuy VoHang Thi-Thuy LeDien DinhPublished in: ITCC (2022)
Keyphrases
- wordnet
- recognizing textual entailment
- semantic similarity
- lexico syntactic
- text documents
- semantic information
- semantic distance
- lexical database
- natural language processing
- co occurrence
- semantic relations
- textual entailment
- semantic relatedness
- word sense disambiguation
- semantic similarity measure
- lexical resources
- automatically created
- word similarity
- manually constructed
- keywords
- semantic network
- semantic content
- text summarization
- word sense
- heuristic rules
- similarity measure
- named entity recognition
- text processing
- text mining
- lexical knowledge
- text corpus
- word pairs
- knowledge base
- sentence level
- document representation
- lexical chains
- lexical information
- information retrieval
- semantic representations
- semantically related
- noun phrases
- natural language
- semantic features
- part of speech
- vector space model
- similarity function
- named entities
- question answering
- information extraction
- search engine
- machine learning