arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.16463cs.CL
收藏

基于叠加概念判别的少样本命名实体识别

Few-shot Named Entity Recognition via Superposition Concept Discrimination

University of Chinese Academy of Sciences(中国科学院大学);State Key Laboratory of Computer Science(计算机科学国家重点实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Ricoh Software Research Center Beijing Co., Ltd(理光软件研究中心(北京)有限公司)

Jiawei Chen, Hongyu Lin, Xianpei Han, Yaojie Lu, Shanshan Jiang, Bin Dong, Le Sun

AI总结:

本文提出主动学习框架 SuperCD,通过概念提取器和叠加实例检索器从大规模语料库中识别并检索叠加概念实例,有效解决了少样本命名实体识别中的精确泛化问题,显著提升了模型性能。

摘要:

Few-shot NER 旨在仅用有限数量的示例实例来识别目标类型的实体。然而,少样本 NER 受到内在精确泛化问题的严重挑战,即由于信息不足产生的歧义,很难准确确定所需的目标类型。本文提出 Superposition Concept Discriminator (SuperCD),通过主动学习范式解决上述挑战。具体而言,首先引入概念提取器从示例实例中识别叠加概念,每个概念对应一个可能的泛化边界。然后应用叠加实例检索器,从大规模文本语料库中检索这些叠加概念的对应实例。最后,要求标注者对检索到的实例进行标注,并将这些标注实例与原始示例实例一起用于学习 FS-NER 模型。为此,我们利用大规模公开可用的知识库来学习通用概念提取器和叠加实例检索器。实验表明,SuperCD 能有效从示例实例中识别叠加概念,从大规模语料库中检索叠加实例,并以最少的额外工作量显著提升少样本 NER 性能。

英文摘要:

Few-shot NER aims to identify entities of target types with only limited number of illustrative instances. Unfortunately, few-shot NER is severely challenged by the intrinsic precise generalization problem, i.e., it is hard to accurately determine the desired target type due to the ambiguity stemming from information deficiency. In this paper, we propose Superposition Concept Discriminator (SuperCD), which resolves the above challenge via an active learning paradigm. Specifically, a concept extractor is first introduced to identify superposition concepts from illustrative instances, with each concept corresponding to a possible generalization boundary. Then a superposition instance retriever is applied to retrieve corresponding instances of these superposition concepts from large-scale text corpus. Finally, annotators are asked to annotate the retrieved instances and these annotated instances together with original illustrative instances are used to learn FS-NER models. To this end, we learn a universal concept extractor and superposition instance retriever using a large-scale openly available knowledge bases. Experiments show that SuperCD can effectively identify superposition concepts from illustrative instances, retrieve superposition instances from large-scale corpus, and significantly improve the few-shot NER performance with minimal additional efforts.

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。

↑