Topic-Based Clustering of Japanese Sentences Using Sentence-BERT.
Kenshin TsumurayaMiki AmanoMinoru UeharaYoshihiro AdachiPublished in: CANDARW (2022)
Keyphrases
- automatic summarization
- multi document summarization
- natural language
- multidocument summarization
- document set
- sentence level
- text summarization
- k means
- word frequency
- topic detection
- clustering algorithm
- document level
- document clustering
- syntactic information
- sentence similarity
- linguistic features
- natural language sentences
- clustering method
- syntactic analysis
- document summarization
- single document summarization
- data points
- document summaries
- sentence retrieval
- parse tree
- text corpus
- syntactic structures
- noun phrases
- sentence compression
- probabilistic context free grammars
- discourse structure
- syntactic features
- named entities
- phrase structure
- dependency relations
- training corpus
- syntactic parsing
- cross document
- automatic text summarization
- dependency tree
- sentence extraction
- sentiment analysis
- semantic analysis
- information retrieval
- topic models