Event Temporal Relation Extraction based on Retrieval-Augmented on LLMs
This work addresses the problem of ambiguous temporal relation extraction for natural language processing researchers, representing an incremental improvement over traditional manual methods.
The paper tackles the challenge of extracting event temporal relations by introducing a retrieval-augmented approach that uses knowledge from large language models to enhance prompt templates and verbalizers, leading to improved performance across three datasets.
Event temporal relation (TempRel) is a primary subject of the event relation extraction task. However, the inherent ambiguity of TempRel increases the difficulty of the task. With the rise of prompt engineering, it is important to design effective prompt templates and verbalizers to extract relevant knowledge. The traditional manually designed templates struggle to extract precise temporal knowledge. This paper introduces a novel retrieval-augmented TempRel extraction approach, leveraging knowledge retrieved from large language models (LLMs) to enhance prompt templates and verbalizers. Our method capitalizes on the diverse capabilities of various LLMs to generate a wide array of ideas for template and verbalizer design. Our proposed method fully exploits the potential of LLMs for generation tasks and contributes more knowledge to our design. Empirical evaluations across three widely recognized datasets demonstrate the efficacy of our method in improving the performance of event temporal relation extraction tasks.