Topic Judgment Helps Question Similarity Prediction in Medical FAQ Dialogue Systems
2019-11
会议录名称2019 INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW)
ISSN2375-9232
页码966-972
发表状态已发表
DOI10.1109/ICDMW.2019.00140
摘要

As a prominent application of artificial intelligence in healthcare, medical dialogue systems have a promising future. In this paper, we built a medical Frequently Asked Questions (FAQ) dialogue system using an XGBoost classifier based on handcrafted features. Moreover, we propose to improve accuracy in domain-specific information retrieval by adding a topic judgment module to general sentence similarity prediction. As the size of the labeled medical corpus in Chinese is very limited, we built a corpus of Chinese medical FAQ from mvyxws https://www.mvyxws.com/ and annotated a small part of it. We applied our topic judgment module to the XGBoost model, a general sentence similarity model, and Baidu short text similarity API. Testing on two datasets, the models can be improved by adding the topic judgment in most cases.

会议地点Beijing, China
会议日期8-11 Nov. 2019
URL查看原文
收录类别EI
语种英语
出版者IEEE Computer Society
EI入藏号20200608123342
EI主题词Natual Language Processing
EI分类号Data Processing and Image Processing:723.2
原始文献类型Conference article (CA)
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/104297
专题信息科学与技术学院
信息科学与技术学院_硕士生
信息科学与技术学院_PI研究组_郑杰组
通讯作者Jie Zheng
作者单位
1.School of Information Science and Technology, ShanghaiTech University
2.School of Physics, University of Electronic Science and Technology China
3.R & D, XiaoDuoAI
第一作者单位信息科学与技术学院
通讯作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Lin Zhu,Xinnan Dai,Qihao Huang,et al. Topic Judgment Helps Question Similarity Prediction in Medical FAQ Dialogue Systems[C]:IEEE Computer Society,2019:966-972.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Lin Zhu]的文章
[Xinnan Dai]的文章
[Qihao Huang]的文章
百度学术
百度学术中相似的文章
[Lin Zhu]的文章
[Xinnan Dai]的文章
[Qihao Huang]的文章
必应学术
必应学术中相似的文章
[Lin Zhu]的文章
[Xinnan Dai]的文章
[Qihao Huang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。