Stack-based Multi-layer Attention for Transition-based Dependency Parsing

Zhirui Zhang, Shujie Liu, Mu Li, Ming Zhou, Enhong Chen


Abstract
Although sequence-to-sequence (seq2seq) network has achieved significant success in many NLP tasks such as machine translation and text summarization, simply applying this approach to transition-based dependency parsing cannot yield a comparable performance gain as in other state-of-the-art methods, such as stack-LSTM and head selection. In this paper, we propose a stack-based multi-layer attention model for seq2seq learning to better leverage structural linguistics information. In our method, two binary vectors are used to track the decoding stack in transition-based parsing, and multi-layer attention is introduced to capture multiple word dependencies in partial trees. We conduct experiments on PTB and CTB datasets, and the results show that our proposed model achieves state-of-the-art accuracy and significant improvement in labeled precision with respect to the baseline seq2seq model.
Anthology ID:
D17-1175
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1677–1682
Language:
URL:
https://aclanthology.org/D17-1175
DOI:
10.18653/v1/D17-1175
Bibkey:
Cite (ACL):
Zhirui Zhang, Shujie Liu, Mu Li, Ming Zhou, and Enhong Chen. 2017. Stack-based Multi-layer Attention for Transition-based Dependency Parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1677–1682, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Stack-based Multi-layer Attention for Transition-based Dependency Parsing (Zhang et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1175.pdf
Data
Penn Treebank