Structured lexical similarity via convolution kernels on dependency trees

Danilo Croce, Alessandro Moschitti, Roberto Basili

Research output: Chapter in Book/Report/Conference proceedingConference contribution

89 Citations (Scopus)

Abstract

A central topic in natural language processing is the design of lexical and syntactic features suitable for the target application. In this paper, we study convolution dependency tree kernels for automatic engineering of syntactic and semantic patterns exploiting lexical similarities. We define efficient and powerful kernels for measuring the similarity between dependency structures, whose surface forms of the lexical nodes are in part or completely different. The experiments with such kernels for question classification show an unprecedented results, e.g. 41% of error reduction of the former state-of-the-art. Additionally, semantic role classification confirms the benefit of semantic smoothing for dependency kernels.

Original languageEnglish
Title of host publicationEMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Pages1034-1046
Number of pages13
Publication statusPublished - 3 Oct 2011
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2011 - Edinburgh, United Kingdom
Duration: 27 Jul 201131 Jul 2011

Publication series

NameEMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Other

OtherConference on Empirical Methods in Natural Language Processing, EMNLP 2011
CountryUnited Kingdom
CityEdinburgh
Period27/7/1131/7/11

    Fingerprint

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Cite this

Croce, D., Moschitti, A., & Basili, R. (2011). Structured lexical similarity via convolution kernels on dependency trees. In EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 1034-1046). (EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).