arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03181cs.CL
收藏

基于联合推理的疾病问答系统

A Joint-Reasoning based Disease Q&A System

National University of Singapore(新加坡国立大学)

Prakash Chandra Sukhwal, Vaibhav Rajan, Atreyi Kankanhalli

AI总结:

本文提出一种联合语言模型与知识图谱的自动化疾病问答系统,通过联合推理方法提升回答质量,实验表明其性能优于ChatGPT等基准系统。

摘要:

医学问答助手通过自然语言处理及相关技术,综合多个来源的信息来回答普通用户的健康相关查询。它们可以作为重要工具,缓解错误信息、信息过载和医学语言复杂等问题,从而满足普通用户的信息需求,同时减轻医疗专业人员的负担。作为此类助手引擎的问答系统,通常使用语言模型或知识图谱,尽管这两种方法可以互补。基于语言模型的问答系统擅长理解复杂问题并提供格式良好的答案,但容易出现事实性错误。基于知识图谱的问答系统能够很好地表示事实,但大多局限于使用预先创建的模板回答简答题。虽然少数研究已将语言模型和知识图谱方法联合用于基于文本的问答,但这是为了回答多项选择题。现有问答系统在自动化和性能方面也存在局限性。我们通过设计一种新颖的自动化疾病问答系统来应对这些挑战,该系统通过联合推理方法有效利用语言模型和知识图谱技术,回答适合普通用户的疾病相关问题。我们使用一系列质量指标对该系统进行评估,证明了其相对于基准系统(包括流行的ChatGPT)的有效性。

英文摘要:

Medical question answer (QA) assistants respond to lay users' health-related queries by synthesizing information from multiple sources using natural language processing and related techniques. They can serve as vital tools to alleviate issues of misinformation, information overload, and complexity of medical language, thus addressing lay users' information needs while reducing the burden on healthcare professionals. QA systems, the engines of such assistants, have typically used either language models (LMs) or knowledge graphs (KG), though the approaches could be complementary. LM-based QA systems excel at understanding complex questions and providing well-formed answers, but are prone to factual mistakes. KG-based QA systems, which represent facts well, are mostly limited to answering short-answer questions with pre-created templates. While a few studies have jointly used LM and KG approaches for text-based QA, this was done to answer multiple-choice questions. Extant QA systems also have limitations in terms of automation and performance. We address these challenges by designing a novel, automated disease QA system which effectively utilizes both LM and KG techniques through a joint-reasoning approach to answer disease-related questions appropriate for lay users. Our evaluation of the system using a range of quality metrics demonstrates its efficacy over benchmark systems, including the popular ChatGPT.

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。

↑