TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems

TL;DR

TemPrompt is a multi-task prompt learning framework that enhances temporal relation extraction by leveraging prompt tuning and contrastive learning, effectively addressing data scarcity and improving performance in crowdsourcing systems.

Contribution

It introduces a novel task-oriented prompt construction method and auxiliary temporal reasoning tasks to improve TRE with limited data in crowdsourcing contexts.

Findings

Outperforms baseline models in standard and few-shot settings

Effective in crowdsourcing scenarios like PCB manufacturing

Enhances focus on events and temporal cues

Abstract

Temporal relation extraction (TRE) aims to grasp the evolution of events or actions, and thus shape the workflow of associated tasks, so it holds promise in helping understand task requests initiated by requesters in crowdsourcing systems. However, existing methods still struggle with limited and unevenly distributed annotated data. Therefore, inspired by the abundant global knowledge stored within pre-trained language models (PLMs), we propose a multi-task prompt learning framework for TRE (TemPrompt), incorporating prompt tuning and contrastive learning to tackle these issues. To elicit more effective prompts for PLMs, we introduce a task-oriented prompt construction approach that thoroughly takes the myriad factors of TRE into consideration for automatic prompt generation. In addition, we design temporal event reasoning in the form of masked language modeling as auxiliary tasks to bolster the model's focus on events and temporal cues. The experimental results demonstrate that TemPrompt outperforms all compared baselines across the majority of metrics under both standard and few-shot settings. A case study on designing and manufacturing printed circuit boards is provided to validate its effectiveness in crowdsourcing scenarios.