Wu, Taizhong and Zhou, Junsheng and Qu, Weiguang and Gu, Yanhui and Li, Bin and Zhong, Huilin and Long, Yunfei (2021) Improving AMR parsing by exploiting the dependency parsing as an auxiliary task. Multimedia Tools and Applications, 80 (20). pp. 30827-30838. DOI https://doi.org/10.1007/s11042-020-09967-3
Wu, Taizhong and Zhou, Junsheng and Qu, Weiguang and Gu, Yanhui and Li, Bin and Zhong, Huilin and Long, Yunfei (2021) Improving AMR parsing by exploiting the dependency parsing as an auxiliary task. Multimedia Tools and Applications, 80 (20). pp. 30827-30838. DOI https://doi.org/10.1007/s11042-020-09967-3
Wu, Taizhong and Zhou, Junsheng and Qu, Weiguang and Gu, Yanhui and Li, Bin and Zhong, Huilin and Long, Yunfei (2021) Improving AMR parsing by exploiting the dependency parsing as an auxiliary task. Multimedia Tools and Applications, 80 (20). pp. 30827-30838. DOI https://doi.org/10.1007/s11042-020-09967-3
Abstract
Abstract meaning representations (AMRs) represent sentence semantics as rooted labeled directed acyclic graphs. Though there is a strong correlation between the AMR graph of a sentence and its corresponding dependency tree, the recent neural network AMR parsers do neglect the exploitation of dependency structure information. In this paper, we explore a novel approach to exploiting dependency structures for AMR parsing. Unlike traditional pipeline models, we treat dependency parsing as an auxiliary task for AMR parsing under the multi-task learning framework by sharing neural network parameters and selectively extracting syntactic representation by the attention mechanism. Particularly, to balance the gradients and focus on the AMR parsing task, we present a new dynamical weighting scheme in the loss function. The experimental results on the LDC2015E86 and LDC2017T10 dataset show that our dependency-auxiliary AMR parser significantly outperforms the baseline and its pipeline counterpart, and demonstrate that the neural AMR parsers can be greatly boosted with the help of effective methods of integrating syntax.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Abstract meaning representations; Multi-task learning; Dependency-auxiliary AMR parser; Neural network |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 03 Oct 2023 15:08 |
Last Modified: | 30 Oct 2024 17:17 |
URI: | http://repository.essex.ac.uk/id/eprint/35168 |