arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.18702cs.IRcs.CL
收藏

面向零样本命名实体识别的协作式多智能体框架

A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition

University of Amsterdam(阿姆斯特丹大学);Shandong University(山东大学);Leiden University(莱顿大学)

Zihan Wang, Ziqi Zhao, Yougang Lyu, Zhumin Chen, Maarten de Rijke, Zhaochun Ren

AI总结:

本文提出协作式多智能体框架CMAS,通过自标注、类型特征提取、示例判别和整体预测四个智能体,解决零样本NER中上下文关联忽视和示例误用问题,在六个基准上显著提升性能。

摘要:

零样本命名实体识别(NER)旨在从未标注的文本语料库中开发实体识别系统。由于人工干预极少,这一任务面临巨大挑战。近期研究通过设计专门的提示模板,将大型语言模型(LLMs)应用于零样本NER,并通过引入自标注示例来提升模型的自学习能力。然而,仍存在两个重要挑战:(i)实体周围上下文之间的关联被忽视,导致类型预测错误或实体遗漏。(ii)通过基于浅层相似性的策略检索到的任务示例被不加区分地使用,严重误导LLMs在推理过程中的判断。本文提出协作式多智能体系统(CMAS),一种用于零样本NER的新颖框架,利用多个智能体的集体智慧来解决上述挑战。CMAS包含四个主要智能体:(i)自标注器,(ii)类型相关特征(TRF)提取器,(iii)示例判别器,以及(iv)整体预测器。为显式捕获实体周围上下文之间的关联,CMAS将NER重新构建为两个子任务:识别命名实体以及识别目标句子中实体类型相关特征。为实现对示例的可控利用,建立了一个示例判别器,融入自我反思机制,自动评估目标句子的有用性得分。实验结果表明,CMAS在六个基准上显著提升了零样本NER性能,涵盖领域特定和通用领域场景。此外,CMAS在少样本设置和不同LLM骨干下也展现了其有效性。

英文摘要:

Zero-shot named entity recognition (NER) aims to develop entity recognition systems from unannotated text corpora. This task presents substantial challenges due to minimal human intervention. Recent work has adapted large language models (LLMs) for zero-shot NER by crafting specialized prompt templates. It advances model self-learning abilities by incorporating self-annotated demonstrations. However, two important challenges persist: (i) Correlations between contexts surrounding entities are overlooked, leading to wrong type predictions or entity omissions. (ii) The indiscriminate use of task demonstrations, retrieved through shallow similarity-based strategies, severely misleads LLMs during inference. In this paper, we introduce the cooperative multi-agent system (CMAS), a novel framework for zero-shot NER that uses the collective intelligence of multiple agents to address the challenges outlined above. CMAS has four main agents: (i) a self-annotator, (ii) a type-related feature (TRF) extractor, (iii) a demonstration discriminator, and (iv) an overall predictor. To explicitly capture correlations between contexts surrounding entities, CMAS reformulates NER into two subtasks: recognizing named entities and identifying entity type-related features within the target sentence. To enable controllable utilization of demonstrations, a demonstration discriminator is established to incorporate the self-reflection mechanism, automatically evaluating helpfulness scores for the target sentence. Experimental results show that CMAS significantly improves zero-shot NER performance across six benchmarks, including both domain-specific and general-domain scenarios. Furthermore, CMAS demonstrates its effectiveness in few-shot settings and with various LLM backbones.

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。

↑