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 2408.02377cs.CLcs.AI
收藏

一种使用大语言模型进行关系抽取领域自适应的少样本方法

A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models

Department of Mathematics and Computer Science, University of Cagliari, Cagliari, Italy(数学与计算机科学系,卡利亚里大学,卡利亚里,意大利);Institute of Data Science and Artificial Intelligence (DATAI), Universidad de Navarra, Pamplona, Spain(数据科学与人工智能研究所(DATAI),纳瓦拉大学,潘普隆,西班牙);European Commission, Joint Research Centre (DG JRC), Ispra (VA), Italy(欧洲委员会,联合研究中心(DG JRC),伊斯普拉(瓦拉),意大利)

Vanni Zavarella, Juan Carlos Gamero-Salinas, Sergio Consoli

AI总结:

本文利用大语言模型的上下文学习进行模式约束数据标注,以少样本策略为AECO领域的关系抽取模型收集领域内训练数据,实验证明该方法能有效支持科学知识图谱生成模型的领域自适应。

摘要:

知识图谱(KGs)已成功应用于复杂科学技术领域的分析,自动知识图谱生成方法通常基于关系抽取模型,这些模型捕获文本中领域实体之间的细粒度关系。虽然这些关系在科学领域间完全适用,但现有模型仅在少数领域特定数据集(如SciERC)上训练,在新目标领域上表现不佳。本文中,我们实验利用大语言模型的上下文学习能力执行模式约束的数据标注,为部署在建筑、施工、工程和运营(AECO)领域研究论文标题和摘要上的基于Transformer的关系抽取模型收集领域内训练实例。通过评估相对于在领域外数据上训练的基线深度学习架构的性能提升,我们表明,通过使用带有结构化提示的少样本学习策略和仅需极少的专家标注,所提出的方法能够潜在地支持科学知识图谱生成模型的领域自适应。

英文摘要:

Knowledge graphs (KGs) have been successfully applied to the analysis of complex scientific and technological domains, with automatic KG generation methods typically building upon relation extraction models capturing fine-grained relations between domain entities in text. While these relations are fully applicable across scientific areas, existing models are trained on few domain-specific datasets such as SciERC and do not perform well on new target domains. In this paper, we experiment with leveraging in-context learning capabilities of Large Language Models to perform schema-constrained data annotation, collecting in-domain training instances for a Transformer-based relation extraction model deployed on titles and abstracts of research papers in the Architecture, Construction, Engineering and Operations (AECO) domain. By assessing the performance gain with respect to a baseline Deep Learning architecture trained on off-domain data, we show that by using a few-shot learning strategy with structured prompts and only minimal expert annotation the presented approach can potentially support domain adaptation of a science KG generation model.

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。

↑