Sentence Similarity Based on Semantic Nets and Corpus Statistics.
Yuhua LiDavid McLeanZuhair BandarJames O'SheaKeeley A. CrockettPublished in: IEEE Trans. Knowl. Data Eng. (2006)
Keyphrases
- sentence level
- linguistic features
- training corpus
- recognizing textual entailment
- text corpus
- natural language
- noun phrases
- document level
- parallel corpus
- semantic roles
- sentence pairs
- word frequency
- part of speech
- probabilistic context free grammars
- automatic summarization
- sentiment analysis
- test set
- predicate argument
- descriptive statistics
- semantic net
- text classification
- syntactic features
- text mining
- semantic parser
- ambiguous words
- manually annotated
- syntactic analysis
- semantic network
- novelty detection
- text corpora