Inproceedings,

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

, , , , , and .
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, page 19--27. Stroudsburg, PA, USA, Association for Computational Linguistics, (2009)

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.

Tags

Users

  • @theodoro
  • @blasp
  • @kde-alumni
  • @thoni
  • @diego_ma
  • @dawa
  • @hotho
  • @dbenz

Comments and Reviews