A study on similarity and relatedness using distributional and WordNet-based approaches

return to the website
by Eneko Agirre, Enrique Alfonseca, Keith Hall, Jana Kravalova, Marius Paşca, Aitor Soroa
Abstract:
This paper presents and compares WordNet-based and distributional similarity approaches. The strengths and weaknesses of each approach regarding similarity and relatedness tasks are discussed, and a combination is presented. Each of our methods independently provide the best results in their class on the RG and WordSim353 datasets, and a supervised combination of them yields the best published results on all datasets. Finally, we pioneer cross-lingual similarity, showing that our methods are easily adapted for a cross-lingual task with minor losses.
Reference:
A study on similarity and relatedness using distributional and WordNet-based approaches (Eneko Agirre, Enrique Alfonseca, Keith Hall, Jana Kravalova, Marius Paşca, Aitor Soroa), In Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics on - NAACL 09, Association for Computational Linguistics, 2009.
Bibtex Entry:
@inproceedings{Agirre2009,
abstract = {This paper presents and compares WordNet-based and distributional similarity approaches. The strengths and weaknesses of each approach regarding similarity and relatedness tasks are discussed, and a combination is presented. Each of our methods independently provide the best results in their class on the RG and WordSim353 datasets, and a supervised combination of them yields the best published results on all datasets. Finally, we pioneer cross-lingual similarity, showing that our methods are easily adapted for a cross-lingual task with minor losses.},
address = {Morristown, NJ, USA},
author = {Agirre, Eneko and Alfonseca, Enrique and Hall, Keith and Kravalova, Jana and Paşca, Marius and Soroa, Aitor},
booktitle = {Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics on - NAACL 09},
doi = {10.3115/1620754.1620758},
isbn = {9781932432411},
keywords = {Benchmark Rubeinstein and GoodEnough,SML-LIB-BIBLIO,Semantic Similarity,lang:ENG,wordnet,wordsim353},
mendeley-tags = {Benchmark Rubeinstein and GoodEnough,SML-LIB-BIBLIO,Semantic Similarity,lang:ENG,wordnet,wordsim353},
pages = {19},
publisher = {Association for Computational Linguistics},
title = {{A study on similarity and relatedness using distributional and WordNet-based approaches}},
year = {2009}
}
Powered by bibtexbrowser