RST Discourse Parsing with Second-Stage EDU-Level Pre-training
Nan Yu, Meishan Zhang, Guohong Fu, Min Zhang · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
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 pretraining 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. 1