Conceptual Retrieval for Chinese Frequently Asked Questions in Healthcare

• Main Authors: Shu-Ling Lin, 林書伶
• Other Authors: Rey-Long Liu
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/40641954117830314720

碩士 === 慈濟大學 === 醫學資訊學系碩士班 === 101 === Healthcare information needs of users are often in question form. To reduce the burden of healthcare professionals in answering the questions, many health information websites collect and maintain a database of frequently asked questions (FAQs) asked by the users and answered by the healthcare professionals. However, with the increasing amount of FAQs, users are difficult to read all the FAQs to obtain the required information. In this thesis, we propose a technique ECA to rank Chinese healthcare FAQs with respect to questions of users so that relevant FAQs and their answers can be retrieved for the users. ECA considers three types of essential concepts in Chinese healthcare FAQs, including event, condition, and aspect. By recognizing the three types of essential concepts, ECA can improve the performance of various kinds of FAQ retrievers. Empirical evaluation on thousands of Chinese healthcare FAQs show that ECA can significantly enhance several kinds of FAQ retrievers. The contribution is significant to the utility of the healthcare knowledge in the large amount of healthcare FAQs.