计算机工程与应用2024，Vol.60Issue(20)：160-167,8.DOI:10.3778/j.issn.1002-8331.2307-0047
DPMN:面向重叠关系抽取问题的多任务学习网络
DPMN:Multi-Task Learning Network for Problem of Overlapping Relation Extraction
摘要
Abstract
As one of the basic components of natural language processing,relation extraction aims to extract relation facts from a given unstructured text.In practical applications,there is a lack of entity information at the sentence level,and there are often scenarios where a single sentence contains multiple overlapping relation triplets.Relation triplets can gen-erate multiple cross overlaps,making relation extraction tasks more challenging.Early research uses pipeline method to process,which not only ignores the relevance of entity recognition and relationship prediction,but also is vulnerable to propagation of uncertainty.This paper proposes a multi-task learning network(DPMN)based on dependency parsing,which can identify entity span more accurately by dependency parsing,enrich relation semantics,and have multi-task learning strategies to enhance the interaction between various subtasks.Compared with the baseline model,DPMN has better performance in relation triplet extraction,which alleviates the problem of overlapping relations to some extent.关键词
关系抽取/多任务学习/依赖解析/重叠关系Key words
relation extraction/multi-task learning/dependency parsing/overlapping relation分类
信息技术与安全科学引用本文复制引用
李雅杰,唐国根,李平..DPMN:面向重叠关系抽取问题的多任务学习网络[J].计算机工程与应用,2024,60(20):160-167,8.基金项目
国家自然科学基金(62276099) （62276099）
四川省自然科学基金面上项目(2023NSFSC0501). （2023NSFSC0501）
