Transition-based dependency parsing with heuristic backtracking

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Buckman, Jacobca
  • dc.contributor.author Ballesteros, Miguelca
  • dc.contributor.author Dyer, Chrisca
  • dc.date.accessioned 2017-02-07T17:31:14Z
  • dc.date.available 2017-02-07T17:31:14Z
  • dc.date.issued 2016ca
  • dc.description Comunicació presentada a Conference on Empirical Methods in Natural Language Processingca
  • dc.description.abstract We introduce a novel approach to the decoding problem in transition-based parsing: heuristic backtracking. This algorithm uses a series of partial parses on the sentence to locate the best candidate parse, using confidence estimates/nof transition decisions as a heuristic to guide the starting points of the search. This allows us to achieve a parse accuracy comparable to beam search, despite using fewer transitions. When used to augment a Stack-LSTM transition-based parser, the parser shows an unlabeled attachment score of up to 93.30% for English and 87.61% for Chinese.en
  • dc.description.sponsorship Miguel Ballesteros was supported by the European Commission under the contract numbers FP7-/nICT-610411 (project MULTISENSOR) and H2020-RIA-645012 (project KRISTINA).en
  • dc.format.mimetype application/pdfca
  • dc.identifier.citation Buckman J, Ballesteros M, Dyer C. Transition-based dependency parsing with heuristic backtracking. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing; 2016 Nov 1-5; Austin, Texas, USA. Stroudsburg (USA): Association for Computational Linguistics (ACL); 2016. p. 2313-18.ca
  • dc.identifier.uri http://hdl.handle.net/10230/28074
  • dc.language.iso engca
  • dc.publisher ACL (Association for Computational Linguistics)ca
  • dc.relation.ispartof Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing; 2016 Nov 1-5; Austin, Texas, USA. Stroudsburg (USA): Association for Computational Linguistics (ACL); 2016. p. 2313-18.en
  • dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012
  • dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/610411
  • dc.rights © ACL, Creative Commons Attribution 4.0 Licenseca
  • dc.rights.accessRights info:eu-repo/semantics/openAccessca
  • dc.rights.uri http://creativecommons.org/licenses/by/4.0/
  • dc.subject.other Lingüística computacionalca
  • dc.subject.other Tractament del llenguatge natural (Informàtica)ca
  • dc.title Transition-based dependency parsing with heuristic backtrackingca
  • dc.type info:eu-repo/semantics/conferenceObjectca
  • dc.type.version info:eu-repo/semantics/publishedVersionca