LIPN-CORE: Semantic Text Similarity using n-grams, WordNet, Syntactic Analysis, ESA and Information Retrieval based Features

Davide Buscaldi (1) , Joseph Le Roux (1) , Jorge J. García Flores (1) , Adrian Popescu (2)

1 LIPN - Laboratoire d'Informatique de Paris-Nord
2 DIASI (CEA, LIST) - Département Intelligence Ambiante et Systèmes Interactifs

This paper describes the system used by the LIPN team in the Semantic Textual Similarity task at SemEval 2013. It uses a support vector regression model, combining different text similarity measures that constitute the features. These measures include simple distances like Levenshtein edit distance, cosine, Named Entities overlap and more complex distances like Explicit Semantic Analysis, WordNet-based similarity, IR-based similarity, and a similarity measure based on syntactic dependencies.

Mots clés: Similarité Sémantique

Domaines: Traitement du texte et du document

Davide Buscaldi, Joseph Le Roux, Jorge J. García Flores, Adrian Popescu. LIPN-CORE: Semantic Text Similarity using n-grams, WordNet, Syntactic Analysis, ESA and Information Retrieval based Features. Second Joint Conference on Lexical and Computational Semantics, Jun 2013, Atlanta, United States. pp.63. ⟨hal-00825054⟩