Transition-based dependency parsing with stack long short-term memory

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Dyer, Chrisca
  • dc.contributor.author Ballesteros, Miguelca
  • dc.contributor.author Ling, Wca
  • dc.contributor.author Matthews, Aca
  • dc.contributor.author Smith, Noah A.ca
  • dc.date.accessioned 2017-01-26T15:38:39Z
  • dc.date.available 2017-01-26T15:38:39Z
  • dc.date.issued 2015ca
  • dc.description.abstract We propose a technique for learning representations of parser states in transitionbased dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks— the stack LSTM. Like the conventional stack data structures used in transitionbased parsing, elements can be pushed to/nor popped from the top of the stack in constant time, but, in addition, an LSTM maintains a continuous space embedding of the stack contents. This lets us formulate an efficient parsing model that captures three facets of a parser’s state: (i) unbounded look-ahead into the buffer of incoming words, (ii) the complete history of actions taken by the parser, and (iii) the complete contents of the stack of partially built tree fragments, including their internal/nstructures. Standard backpropagation techniques are used for training and yield state-of-the-art parsing performance.en
  • dc.description.sponsorship This work was sponsored in part by the U. S. Army Research Laboratory and the U. S. Army Research Office/nunder contract/grant number W911NF-10-1-0533, and in part by NSF CAREER grant IIS-1054319./nMiguel Ballesteros is supported by the European Commission under the contract numbers FP7-ICT-610411 (project MULTISENSOR) and H2020-RIA-645012 (project KRISTINA).en
  • dc.format.mimetype application/pdfca
  • dc.identifier.citation Dyer C, Ballesteros M, Ling W, Matthews A, Smith NA. Transition-based dependency parsing with stack long short-term memory. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Volume 1: Long Papers; 2015 July 26-31; Beijing (China). [place unknown]: ACL; 2015. p. 334-43.ca
  • dc.identifier.uri http://hdl.handle.net/10230/28001
  • dc.language.iso engca
  • dc.publisher ACL (Association for Computational Linguistics)ca
  • dc.relation.ispartof Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Volume 1: Long Papers; 2015 July 26-31; Beijing (China). [place unknown]: ACL; 2015. p. 334-43.
  • dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012ca
  • dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/610411
  • dc.rights © ACL, Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Licenseca
  • dc.rights.accessRights info:eu-repo/semantics/openAccessca
  • dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/
  • dc.subject.other Lingüística computacionalca
  • dc.subject.other Tractament del llenguatge natural (Informàtica)ca
  • dc.title Transition-based dependency parsing with stack long short-term memoryca
  • dc.type info:eu-repo/semantics/conferenceObjectca
  • dc.type.version info:eu-repo/semantics/publishedVersionca

Col·leccions

Congressos (Departament de Tecnologies de la Informació i les Comunicacions)
Documents OpenAIRE (Open Access Infrastructure for Research in Europe)