arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.13405cs.CL
收藏

统一 taxonomy 引导的指令微调框架用于实体集合扩展与 taxonomy 扩展

A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Texas A&M University(德克萨斯农工大学)

Yanzhen Shen, Yu Zhang, Yunyi Zhang, Jiawei Han

AI总结:

本文提出 TaxoInstruct 框架,通过识别“寻找兄弟”和“寻找父级”两个共同技能,统一解决实体集合扩展、taxonomy 扩展和种子引导的 taxonomy 构建三个任务,实验表明其优于任务特定基线。

摘要:

实体集合扩展、taxonomy 扩展和种子引导的 taxonomy 构建是三种代表性任务,可应用于自动用新兴概念填充现有 taxonomy。以往研究将这三者视为独立任务,因此提出的技术通常仅适用于某一特定任务,缺乏泛化性和整体视角。本文旨在为这三个任务提供统一解决方案。具体而言,我们识别出实体集合扩展、taxonomy 扩展和种子引导的 taxonomy 构建所需的两个共同技能:寻找“兄弟”和寻找“父级”。我们提出一个 taxonomy 引导的指令微调框架,教导大型语言模型为查询实体生成兄弟和父级,其中联合预训练过程促进这两种技能的相互增强。在多个基准数据集上的大量实验证明了我们提出的 TaxoInstruct 框架的有效性,其在所有三个任务上均优于任务特定的基线方法。

英文摘要:

Entity set expansion, taxonomy expansion, and seed-guided taxonomy construction are three representative tasks that can be applied to automatically populate an existing taxonomy with emerging concepts. Previous studies view them as three separate tasks. Therefore, their proposed techniques usually work for one specific task only, lacking generalizability and a holistic perspective. In this paper, we aim at a unified solution to the three tasks. To be specific, we identify two common skills needed for entity set expansion, taxonomy expansion, and seed-guided taxonomy construction: finding "siblings" and finding "parents". We propose a taxonomy-guided instruction tuning framework to teach a large language model to generate siblings and parents for query entities, where the joint pre-training process facilitates the mutual enhancement of the two skills. Extensive experiments on multiple benchmark datasets demonstrate the efficacy of our proposed TaxoInstruct framework, which outperforms task-specific baselines across all three tasks.

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。

↑