RST Discourse Parsing with Second-Stage EDU-Level Pre-training

Nan Yu, Meishan Zhang, Guohong Fu, Min Zhang


Abstract
Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP).We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective,leading a 2.1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
Anthology ID:
2022.acl-long.294
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4269–4280
Language:
URL:
https://aclanthology.org/2022.acl-long.294
DOI:
10.18653/v1/2022.acl-long.294
Bibkey:
Cite (ACL):
Nan Yu, Meishan Zhang, Guohong Fu, and Min Zhang. 2022. RST Discourse Parsing with Second-Stage EDU-Level Pre-training. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4269–4280, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
RST Discourse Parsing with Second-Stage EDU-Level Pre-training (Yu et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.294.pdf
Software:
 2022.acl-long.294.software.zip
Code
 yunan4nlp/e-nnrstparser