论文标题
Grasp：使用对话关系提取提示，使用关系语义的指导模型
GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction
论文作者
论文摘要
基于对话的关系提取（对话）任务旨在预测对话中出现的论点对之间的关系。以前的大多数研究都使用微调预训练的语言模型（PLM），仅具有广泛的功能来补充多个演讲者对话的低信息密度。为了有效利用PLM的固有知识，没有额外的层次，并考虑有关参数之间关系的分散的语义提示，我们提出了一个使用PISTING（GRASP）使用关系语义的指导模型。我们采用迅速的微调方法，并捕获给定对话的关系语义线索，并使用1）参数感知的提示标记策略以及2）关系线索检测任务。在实验中，GRASP在对话框数据集上以F1和F1C得分来实现最先进的性能，即使我们的方法仅利用PLM，而无需添加任何额外的层。
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.
