arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04247cs.CL
收藏

UltraWiki:带负种子实体的超细粒度实体集扩展

UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities

Pengcheng Laboratory(鹏城实验室);Shenzhen International Graduate School, Tsinghua University(深圳国际研究生院,清华大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室(深圳))

Yangning Li, Qingsong Lv, Tianyu Yu, Yinghui Li, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, Hui Wang

AI总结:

本文针对超细粒度实体集扩展任务,提出引入负种子实体以消除语义歧义并表达“不想要的”语义,构建了首个大规模数据集UltraWiki,并提出RetExpan与GenExpan基线框架以及对比学习和思维链推理策略。

摘要:

实体集扩展(Entity Set Expansion, ESE)旨在识别与给定种子实体集属于同一语义类别的新实体。传统方法仅依赖正种子实体来表示目标细粒度语义类别,这使得它们难以表示超细粒度语义类别。具体而言,仅仅依赖正种子实体会导致两个固有缺陷:(i)超细粒度语义类别之间存在歧义;(ii)无法定义“不想要的”语义。因此,以往的ESE方法难以应对超细粒度ESE(Ultra-ESE)任务。为了解决这一问题,我们首先在输入中引入负种子实体,使其与正种子实体共同描述超细粒度语义类别。负种子实体通过提供正负属性之间的对比来消除语义歧义。同时,它为表达“不想要的”语义提供了一种直接的方式。为了评估模型在Ultra-ESE上的性能并促进进一步研究,我们还构建了UltraWiki,这是第一个专门为Ultra-ESE定制的大规模数据集。UltraWiki包含50,973个实体和394,097个句子,以及236个超细粒度语义类别,每个类别由3-5个正负种子实体表示。此外,我们提出了基于检索的框架RetExpan和基于生成的框架GenExpan,为Ultra-ESE提供强大的基线。另外,我们设计了两种策略来增强模型对超细粒度实体语义的理解:对比学习和思维链推理。大量实验证实了我们所提策略的有效性,同时也表明Ultra-ESE仍有很大的改进空间。

英文摘要:

Entity Set Expansion (ESE) aims to identify new entities belonging to the same semantic class as the given set of seed entities. Traditional methods solely relied on positive seed entities to represent the target fine-grained semantic class, rendering them tough to represent ultra-fine-grained semantic classes. Specifically, merely relying on positive seed entities leads to two inherent shortcomings: (i) Ambiguity among ultra-fine-grained semantic classes. (ii) Inability to define ``unwanted'' semantics. Hence, previous ESE methods struggle to address the ultra-fine-grained ESE (Ultra-ESE) task. To solve this issue, we first introduce negative seed entities in the inputs, which jointly describe the ultra-fine-grained semantic class with positive seed entities. Negative seed entities eliminate the semantic ambiguity by providing a contrast between positive and negative attributes. Meanwhile, it provides a straightforward way to express ``unwanted''. To assess model performance in Ultra-ESE and facilitate further research, we also constructed UltraWiki, the first large-scale dataset tailored for Ultra-ESE. UltraWiki encompasses 50,973 entities and 394,097 sentences, alongside 236 ultra-fine-grained semantic classes, where each class is represented with 3-5 positive and negative seed entities. Moreover, a retrieval-based framework RetExpan and a generation-based framework GenExpan are proposed to provide powerful baselines for Ultra-ESE. Additionally, we devised two strategies to enhance models' comprehension of ultra-fine-grained entities' semantics: contrastive learning and chain-of-thought reasoning. Extensive experiments confirm the effectiveness of our proposed strategies and also reveal that there remains a large space for improvement in Ultra-ESE.

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。

↑