DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition

TL;DR

This paper introduces DiscoPrompt, a prompt tuning approach that predicts hierarchical paths in implicit discourse relation recognition, significantly improving performance by leveraging the hierarchical structure of discourse labels.

Contribution

It is the first to incorporate hierarchical path prediction into pre-trained language models for IDRR using prompt tuning, enhancing relation recognition accuracy.

Findings

Significant performance improvements over baselines

Effective utilization of hierarchical structure in discourse labels

First application of prompt tuning for hierarchical path prediction

Abstract

Implicit Discourse Relation Recognition (IDRR) is a sophisticated and challenging task to recognize the discourse relations between the arguments with the absence of discourse connectives. The sense labels for each discourse relation follow a hierarchical classification scheme in the annotation process (Prasad et al., 2008), forming a hierarchy structure. Most existing works do not well incorporate the hierarchy structure but focus on the syntax features and the prior knowledge of connectives in the manner of pure text classification. We argue that it is more effective to predict the paths inside the hierarchical tree (e.g., "Comparison -> Contrast -> however") rather than flat labels (e.g., Contrast) or connectives (e.g., however). We propose a prompt-based path prediction method to utilize the interactive information and intrinsic senses among the hierarchy in IDRR. This is the first work that injects such structure information into pre-trained language models via prompt tuning, and the performance of our solution shows significant and consistent improvement against competitive baselines.