Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition

Huibin Ruan, Yu Hong, Yang Xu, Zhen Huang, Guodong Zhou, Min Zhang


Abstract
We tackle implicit discourse relation recognition. Both self-attention and interactive-attention mechanisms have been applied for attention-aware representation learning, which improves the current discourse analysis models. To take advantages of the two attention mechanisms simultaneously, we develop a propagative attention learning model using a cross-coupled two-channel network. We experiment on Penn Discourse Treebank. The test results demonstrate that our model yields substantial improvements over the baselines (BiLSTM and BERT).
Anthology ID:
2020.coling-main.282
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3168–3178
Language:
URL:
https://aclanthology.org/2020.coling-main.282
DOI:
10.18653/v1/2020.coling-main.282
Bibkey:
Cite (ACL):
Huibin Ruan, Yu Hong, Yang Xu, Zhen Huang, Guodong Zhou, and Min Zhang. 2020. Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3168–3178, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition (Ruan et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.282.pdf