Computer Laboratory

Diarmuid Ó Séaghdha

Probabilistic models of similarity in syntactic context


Diarmuid Ó Séaghdha and Anna Korhonen

This paper investigates novel methods for incorporating syntactic information in probabilistic latent variable models of lexical choice and contextual similarity. The resulting models capture the effects of context on the interpretation of a word and in particular its effect on the appropriateness of replacing that word with a potentially related one. Evaluating our techniques on two datasets, we report performance above the prior state of the art for estimating sentence similarity and ranking lexical substitutes.

Erratum: The published version contains a minor typo in equation (16). The version hosted here has been corrected; the published version is still available through the ACL Anthology.

  author = 	 {Diarmuid {\'O S\'eaghdha} and Anna Korhonen},
  title = 	 {Probabilistic models of similarity in syntactic context},
  booktitle = 	 {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-11)},
  year =	 2011,
  address =	 {Edinburgh, UK}