arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.09322cs.CL
收藏

一种基于压缩记忆的事件论元抽取检索方法

A Compressive Memory-based Retrieval Approach for Event Argument Extraction

University of Electronic Science and Technology of China(电子科技大学);National University of Singapore(新加坡国立大学)

Wanlong Liu, Enqi Zhang, Li Zhou, Dingyi Zeng, Shaohuan Cheng, Chen Zhang, Malu Zhang, Wenyu Chen

AI总结:

针对现有基于检索的事件论元抽取方法存在的输入长度限制、检索器与推理模型有差距的问题,提出压缩记忆检索机制,在三个公开数据集上取得了最优性能。

摘要:

近期研究已证明检索增强在事件论元抽取(Event Argument Extraction, EAE)任务中的有效性。然而,现有基于检索的EAE方法存在两大主要局限:(1)输入长度限制;(2)检索器与推理模型之间存在差距。这些问题限制了检索信息的多样性与质量。本文提出一种面向EAE的压缩记忆检索(Compressive Memory-based Retrieval, CMR)机制,用以解决上述两大局限。我们的压缩记忆被设计为可有效缓存检索信息并支持持续更新的动态矩阵,克服了输入长度的限制。此外,在将所有候选示例预加载到压缩记忆后,模型会根据输入查询进一步从记忆中检索并过滤相关信息,弥合了检索器与推理模型之间的差距。大量实验表明,我们的方法在三个公开数据集(RAMS、WikiEvents、ACE05)上取得了新的state-of-the-art性能,显著优于现有基于检索的EAE方法。

英文摘要:

Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap between the retriever and the inference model. These issues limit the diversity and quality of the retrieved information. In this paper, we propose a Compressive Memory-based Retrieval (CMR) mechanism for EAE, which addresses the two limitations mentioned above. Our compressive memory, designed as a dynamic matrix that effectively caches retrieved information and supports continuous updates, overcomes the limitations of the input length. Additionally, after pre-loading all candidate demonstrations into the compressive memory, the model further retrieves and filters relevant information from memory based on the input query, bridging the gap between the retriever and the inference model. Extensive experiments show that our method achieves new state-of-the-art performance on three public datasets (RAMS, WikiEvents, ACE05), significantly outperforming existing retrieval-based EAE methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑