Hierarchical Pointer Net Parsing

Linlin Liu, Xiang Lin, Shafiq Joty, Simeng Han, Lidong Bing

Abstract
Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity. However, the decoder of these parsers has a sequential structure, which does not yield the most appropriate inductive bias for deriving tree structures. In this paper, we propose hierarchical pointer network parsers, and apply them to dependency and sentence-level discourse parsing tasks. Our results on standard benchmark datasets demonstrate the effectiveness of our approach, outperforming existing methods and setting a new state-of-the-art.
Anthology ID:
D19-1093
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1007–1017
Language:
URL:
https://aclanthology.org/D19-1093
DOI:
10.18653/v1/D19-1093
Bibkey:
Cite (ACL):
Linlin Liu, Xiang Lin, Shafiq Joty, Simeng Han, and Lidong Bing. 2019. Hierarchical Pointer Net Parsing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1007–1017, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Pointer Net Parsing (Liu et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/D19-1093.pdf
Attachment:
 D19-1093.Attachment.pdf
Data
Penn Treebank
PDF Search Attachment