Welcome to the UPF Digital Repository

Transition-based dependency parsing with heuristic backtracking

Show simple item record

dc.contributor.author Buckman, Jacob
dc.contributor.author Ballesteros, Miguel
dc.contributor.author Dyer, Chris
dc.date.accessioned 2017-02-07T17:31:14Z
dc.date.available 2017-02-07T17:31:14Z
dc.date.issued 2016
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.
dc.identifier.uri http://hdl.handle.net/10230/28074
dc.description Comunicació presentada a Conference on Empirical Methods in Natural Language Processing
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.
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).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher ACL (Association for Computational Linguistics)
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.
dc.rights © ACL, Creative Commons Attribution 4.0 License
dc.rights.uri http://creativecommons.org/licenses/by/4.0/
dc.subject.other Lingüística computacional
dc.subject.other Tractament del llenguatge natural (Informàtica)
dc.title Transition-based dependency parsing with heuristic backtracking
dc.type info:eu-repo/semantics/conferenceObject
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/610411
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion


This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

Compliant to Partaking