Efficient Second-Order TreeCRF for Neural Dependency Parsing

Yu Zhang, Zhenghua Li, Min Zhang


Abstract
In the deep learning (DL) era, parsing models are extremely simplified with little hurt on performance, thanks to the remarkable capability of multi-layer BiLSTMs in context representation. As the most popular graph-based dependency parser due to its high efficiency and performance, the biaffine parser directly scores single dependencies under the arc-factorization assumption, and adopts a very simple local token-wise cross-entropy training loss. This paper for the first time presents a second-order TreeCRF extension to the biaffine parser. For a long time, the complexity and inefficiency of the inside-outside algorithm hinder the popularity of TreeCRF. To address this issue, we propose an effective way to batchify the inside and Viterbi algorithms for direct large matrix operation on GPUs, and to avoid the complex outside algorithm via efficient back-propagation. Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data. We release our code at https://github.com/yzhangcs/crfpar.
Anthology ID:
2020.acl-main.302
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3295–3305
Language:
URL:
https://aclanthology.org/2020.acl-main.302
DOI:
10.18653/v1/2020.acl-main.302
Bibkey:
Cite (ACL):
Yu Zhang, Zhenghua Li, and Min Zhang. 2020. Efficient Second-Order TreeCRF for Neural Dependency Parsing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3295–3305, Online. Association for Computational Linguistics.
Cite (Informal):
Efficient Second-Order TreeCRF for Neural Dependency Parsing (Zhang et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.302.pdf
Video:
 http://slideslive.com/38928756
Code
 yzhangcs/crfpar +  additional community code
Data
CoNLL-2009Penn TreebankUniversal Dependencies