8
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Arc-swift: A Novel Transition System for Dependency Parsing

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments. Correct individual decisions hence require global information about the sentence context and mistakes cause error propagation. This paper proposes a novel transition system, arc-swift, that enables direct attachments between tokens farther apart with a single transition. This allows the parser to leverage lexical information more directly in transition decisions. Hence, arc-swift can achieve significantly better performance with a very small beam size. Our parsers reduce error by 3.7--7.6% relative to those using existing transition systems on the Penn Treebank dependency parsing task and English Universal Dependencies.

          Related collections

          Most cited references8

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Leveraging Linguistic Structure For Open Domain Information Extraction

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Non-projective dependency parsing using spanning tree algorithms

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Globally Normalized Transition-Based Neural Networks

                Bookmark

                Author and article information

                Journal
                2017-05-11
                Article
                1705.04434
                8c32da19-b37b-407a-861a-738654700e60

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                Accepted at ACL 2017
                cs.CL

                Theoretical computer science
                Theoretical computer science

                Comments

                Comment on this article