Abstract
Syntax has been shown useful for various NLP tasks, while existing work mostly encodes singleton syntactic tree using one hierarchical neural network. In this paper, we investigate a simple and effective method, Knowledge Distillation, to integrate heterogeneous structure knowledge into a unified sequential LSTM encoder. Experimental results on four typical syntax-dependent tasks show that our method outperforms tree encoders by effectively integrating rich heterogeneous structure syntax, meanwhile reducing error propagation, and also outperforms ensemble methods, in terms of both the efficiency and accuracy.- Anthology ID:
- 2020.findings-emnlp.18
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 183–193
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.18
- DOI:
- 10.18653/v1/2020.findings-emnlp.18
- Cite (ACL):
- Hao Fei, Yafeng Ren, and Donghong Ji. 2020. Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 183–193, Online. Association for Computational Linguistics.
- Cite (Informal):
- Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP (Fei et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2020.findings-emnlp.18.pdf
- Data
- OntoNotes 5.0, SST