Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings.
Marco Di GiovanniMarco BrambillaPublished in: CoRR (2021)
Keyphrases
- semantically similar
- natural language
- dependency relations
- semantic similarity
- natural language processing
- social media
- natural language sentences
- pairwise
- sentence similarity
- semantic features
- domain specific
- wordnet
- text corpus
- helmholtz principle
- linguistic patterns
- semantic web
- word frequency
- syntactic analysis
- semantic information
- semantic relations
- training corpus
- semantic roles
- target language
- social networking
- part of speech
- semantic analysis
- semantic network