SERGIOJIMENEZ at SemEval-2016 Task 1: Effectively Combining Paraphrase Database, String Matching, WordNet, and Word Embedding for Semantic Textual Similarity.
Sergio JimenezPublished in: SemEval@NAACL-HLT (2016)
Keyphrases
- wordnet
- word sense disambiguation
- string matching
- semantic similarity
- sense disambiguation
- recognizing textual entailment
- word similarity
- semantic distance
- database
- semantic similarity measure
- semantic information
- co occurrence
- lexical database
- edit distance
- semantic relations
- natural language processing
- keywords
- semantic features
- pattern matching
- semantic relatedness
- word sense
- semantic relationships
- similarity measure
- knowledge base
- word pairs
- cross language information retrieval
- controlled vocabulary
- suffix tree
- text documents
- relational databases
- textual entailment
- computational linguistics
- relatedness measure
- metadata
- target word
- search engine
- semantic roles
- semantically related
- information extraction
- free text
- distance measure
- knn
- xml documents
- natural language
- data structure