GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction

TL;DR

GRASP is a prompt-based fine-tuning method that leverages relational semantics and argument-aware prompts to improve dialogue relation extraction, achieving state-of-the-art results without extra layers.

Contribution

It introduces a novel prompt-based approach with argument-aware prompts and relational clue detection for dialogue relation extraction.

Findings

Achieves state-of-the-art F1 and F1c scores on DialogRE dataset.

Effectively exploits PLMs without additional layers.

Utilizes argument-aware prompts and relational clues for better relation detection.

Abstract

The dialogue-based relation extraction (DialogRE) task aims to predict the relations between argument pairs that appear in dialogue. Most previous studies utilize fine-tuning pre-trained language models (PLMs) only with extensive features to supplement the low information density of the dialogue by multiple speakers. To effectively exploit inherent knowledge of PLMs without extra layers and consider scattered semantic cues on the relation between the arguments, we propose a Guiding model with RelAtional Semantics using Prompt (GRASP). We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with 1) an argument-aware prompt marker strategy and 2) the relational clue detection task. In the experiments, GRASP achieves state-of-the-art performance in terms of both F1 and F1c scores on a DialogRE dataset even though our method only leverages PLMs without adding any extra layers.