Global Transition-based Non-projective Dependency Parsing
View/ Open
Use this link to cite
http://hdl.handle.net/2183/35078Collections
- GI-LYS - Congresos, conferencias, etc. [71]
- OpenAIRE [368]
Metadata
Show full item recordTitle
Global Transition-based Non-projective Dependency ParsingDate
2018Citation
Carlos Gómez-Rodríguez, Tianze Shi, and Lillian Lee. 2018. Global Transition-based Non-projective Dependency Parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2664–2675, Melbourne, Australia. Association for Computational Linguistics.
Abstract
[Absctract]: Shi, Huang, and Lee (2017a) obtained state-of-the-art results for English and Chinese dependency parsing by combining dynamic-programming implementations of transition-based dependency parsers with a minimal set of bidirectional LSTM features. However, their results were limited to projective parsing. In this paper, we extend their approach to support non-projectivity by providing the first practical implementation of the MH4 algorithm, an Opn4q mildly non projective dynamic-programming parser with very high coverage on non-projective treebanks. To make MH4 compatible with minimal transition-based feature sets, we introduce a transition-based interpretation of it in which parser items are mapped to sequences of transitions. We thus obtain the first implementation of global decoding for non-projective transition-based parsing, and demonstrate empirically that it is more effective than its projective counterpart in parsing a number of highly non-projective languages.
Keywords
Dependency parser
Feature sets
Global transitions
Minimal transition
Non-projective dependency parsing
Feature sets
Global transitions
Minimal transition
Non-projective dependency parsing
Description
56th Annual Meeting of the Association for Computational Linguistics, ACL 2018. Melbourne15 July - 20 July 2018.
Editor version
Rights
Atribución 4.0 (CC BY)
ISBN
978-194808732-2