arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.00769cs.CL
收藏

CollabKG:一个用于(事件)知识图谱构建的可学习人机协作信息抽取工具包

CollabKG: A Learnable Human-Machine-Cooperative Information Extraction Toolkit for (Event) Knowledge Graph Construction

Beijing Jiaotong University(北京交通大学)

Xiang Wei, Yufeng Chen, Ning Cheng, Xingyu Cui, Jinan Xu, Wenjuan Han

AI总结:

针对现有信息抽取工具包不支持多任务和自动更新等问题,提出可学习人机协作工具包CollabKG,统一NER、RE和EE任务,结合基于提示的IE技术实现低成本高性能,并显著提升标注质量、效率与稳定性。

摘要:

为了构建或扩展以实体为中心和以事件为中心的知识图谱(KG和EKG),信息抽取(IE)标注工具包是必不可少的。然而,现有的IE工具包存在几个不容忽视的问题,例如不支持多任务、不支持自动更新。在这项工作中,我们提出了CollabKG,一个用于构建KG和EKG的可学习人机协作IE工具包。具体而言,针对多任务问题,CollabKG统一了不同的IE子任务,包括命名实体识别(NER)、实体-关系三元组抽取(RE)和事件抽取(EE),并同时支持KG和EKG。然后,结合先进的基于提示的IE技术,提出了一种以LLM作为辅助机器的人机协作机制,该机制能够提供更低的成本以及更高的性能。最后,由于人与机器之间的双向交互,具备学习能力的CollabKG允许自我更新。此外,CollabKG具有几个吸引人的特性(例如,定制化、免训练、传播等),使系统功能强大、易于使用且具有高生产力。我们在这些特性上将我们的工具包与其他现有工具进行了整体比较。人类评估定量地表明,CollabKG同时显著提高了标注质量、效率和稳定性。

英文摘要:

In order to construct or extend entity-centric and event-centric knowledge graphs (KG and EKG), the information extraction (IE) annotation toolkit is essential. However, existing IE toolkits have several non-trivial problems, such as not supporting multi-tasks, not supporting automatic updates. In this work, we present CollabKG, a learnable human-machine-cooperative IE toolkit for KG and EKG construction. Specifically, for the multi-task issue, CollabKG unifies different IE subtasks, including named entity recognition (NER), entity-relation triple extraction (RE), and event extraction (EE), and supports both KG and EKG. Then, combining advanced prompting-based IE technology, the human-machine-cooperation mechanism with LLMs as the assistant machine is presented which can provide a lower cost as well as a higher performance. Lastly, owing to the two-way interaction between the human and machine, CollabKG with learning ability allows self-renewal. Besides, CollabKG has several appealing features (e.g., customization, training-free, propagation, etc.) that make the system powerful, easy-to-use, and high-productivity. We holistically compare our toolkit with other existing tools on these features. Human evaluation quantitatively illustrates that CollabKG significantly improves annotation quality, efficiency, and stability simultaneously.

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。

↑