Abstract
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 O(n4) mildly nonprojective 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 effective than its projective counterpart in parsing a number of highly non-projective languages.- Anthology ID:
- P18-1248
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2664–2675
- Language:
- URL:
- https://aclanthology.org/P18-1248
- DOI:
- 10.18653/v1/P18-1248
- Cite (ACL):
- 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.
- Cite (Informal):
- Global Transition-based Non-projective Dependency Parsing (Gómez-Rodríguez et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P18-1248.pdf
- Code
- tzshi/mh4-parser-acl18