Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation

20Citations
Citations of this article
56Readers
Mendeley users who have this article in their library.

Abstract

Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDRR as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.

Cite

CITATION STYLE

APA

Jiang, F., Fan, Y., Chu, X., Li, P., & Zhu, Q. (2021). Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation. In EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 2418–2431). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.emnlp-main.187

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free