A study on similarity and relatedness using distributional and WordNet-based approaches
E. Agirre, E. Alfonseca, K. Hall, J. Kravalova, M. Pasca, und A. Soroa. Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Seite 19--27. Stroudsburg, PA, USA, Association for Computational Linguistics, (2009)
Zusammenfassung
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.
Beschreibung
A study on similarity and relatedness using distributional and WordNet-based approaches
