Leveraging knowledge based question answer technology to address user-interactive short domain question in natural language

Abstract

With the rapid growth of the Internet and database technologies in recent years, question answering systems (QAS) have emerged as important applications. Although many QAS have been implemented, little work has been done on the development of a user-centered evaluation for QAS. User-centered evaluation is used to understand a user's needs and identify important dimensions and factors in the development of an information system in order to improve its acceptance. This paper presents the application of understanding of short domain question in natural language to data query. The word segmentation tool, IK Analyzer, which is extended with the obtained domain dictionary, is used to segment the short text questions. From the segmentation results, the keywords are extracted to obtain query target and query requirement of the question and to generate a SQL statement for data query. The method proposed in this paper can be applied to question-answering system based on database and to develop a user-centered evaluation model for QAS from the user's perspective for enhancing the user satisfaction and acceptance of QAS.