摘要
【目的】解决基于深度学习的实体关系抽取方法在古籍小样本场景下,由于依赖大规模标注数据而导致的微调效率低、抽取性能不佳问题。【方法】提出一种基于提示学习和抽取式阅读理解的古籍礼仪实体关系联合抽取方法。首先,将实体识别和关系抽取任务整合至一个抽取式阅读理解框架中,简化模型结构。然后,利用领域知识设计三种轻量级提示策略,有效降低联合抽取任务的复杂度。最后,基于预训练语言模型和全局指针网络构建古籍礼仪实体关系联合抽取模型MPG-GP(MRC-Prompt-GujiBERT with Global Pointer),有效抽取古籍中的礼仪实体关系三元组。【结果】在构建的古籍礼仪实体关系联合抽取数据集上进行实验,本文方法F1值比基线方法提升了0.32~6.05个百分点。【局限】在构建提示模板时,未采用可学习的软提示方式,并且提示设计仍有进一步优化的空间。【结论】所提方法能够有效缓解深度神经网络对大量标注数据的依赖,提升了模型在小样本古籍礼仪实体关系联合抽取任务上的准确性,为古籍低资源场景信息抽取提供了新的方法和思路。
[Objective]This study addresses the challenges of inefficient fine-tuning and suboptimal extraction performance in deep learning-based entity-relation extraction for ancient texts in low-resource scenarios,which mainly stem from dependency on large-scale annotated data.[Methods]We propose a joint extraction framework combining prompt learning and extractive machine reading comprehension(MRC).First,entity recognition and relation extraction tasks are unified into an MRC framework to streamline model architecture.Second,three lightweight prompt strategies are designed using domain-specific knowledge to reduce task complexity.Finally,we develop MPG-GP,a joint extraction model integrating a pre-trained language model with a global pointer network,to effectively extract etiquette entity-relation triples from ancient texts.[Results]Experiments on a custom ancient etiquette entity-relation extraction dataset show F1-score improvements of 0.32%~6.05%over baseline methods.[Limitations]The prompt templates employ fixed patterns rather than learnable soft prompts,and the prompt engineering design warrants further refinement.[Conclusions]Our approach mitigates reliance on large annotated datasets while improving the accuracy of few-shot joint entity-relation extraction for ancient ritual texts,providing a novel solution for information extraction in low-resource historical documents.
作者
斯日古楞
林民
郭振东
张树钧
Siriguleng;Lin Min;Guo Zhendong;Zhang Shujun(School of Chinese Language and Literature,Inner Mongolia Normal University,Hohhot 010022,China;College of Computer Science and Technology,Inner Mongolia Minzu University,Tongliao 028000,China;Inner Mongolia Electronic Information Vocational Technical College,Hohhot 010070,China;School of Computer Science and Technology,Hainan University,Haikou 570228,China;College of Computer Science and Technology,Inner Mongolia Normal University,Hohhot 010022,China)
出处
《数据分析与知识发现》
北大核心
2025年第3期147-159,共13页
Data Analysis and Knowledge Discovery
基金
国家自然科学基金项目(项目编号:62266033)
内蒙古自治区高校科研项目(项目编号:NJZY23101)
内蒙古师范大学研究生科研创新基金项目(项目编号:CXJJB21013)的研究成果之一。
