MELODI : A Supervised Distributional Approach for Free Paraphrasing of Noun Compounds

Tim van de Cruys (1) , Stergos Afantenos (1, 2) , Philippe Muller (1)

1 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
2 UT3 - Université Toulouse III - Paul Sabatier

This paper describes the system submitted by the MELODI team for the SemEval-2013 Task 4 : Free Paraphrases of Noun Compounds (Hendrickx et al., 2013). Our approach combines the strength of an unsupervised distributional word space model with a supervised maximum-entropy classification model; the distributional model yields a feature representation for a particular compound noun, which is subsequently used by the classifier to induce a number of appropriate paraphrases.

Mots clés: Free Paraphrasing of Noun Compounds

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Logique en informatique [cs.LO]; Informatique et langage [cs.CL]

Tim van de Cruys, Stergos Afantenos, Philippe Muller. MELODI : A Supervised Distributional Approach for Free Paraphrasing of Noun Compounds. 7th International Workshop on Semantic Evaluation (SemEval 2013) in : 2nd Joint Conference on Lexical and Computational Semantics (SEM 2013), Jun 2013, Atlanta, GA, United States. pp. 144-147. ⟨hal-01231760⟩