Skip to Main content Skip to Navigation
Conference papers

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

Abstract : 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.
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01231760
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, November 20, 2015 - 4:27:31 PM
Last modification on : Thursday, March 18, 2021 - 2:25:05 PM
Long-term archiving on: : Friday, April 28, 2017 - 7:09:51 PM

File

vanDeCruys_12593.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01231760, version 1
  • OATAO : 12593

Citation

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⟩

Share

Metrics

Record views

177

Files downloads

118