Abstract: Knowledge graph (KG) is one of key technologies for intelligently answering questions, which can reduce customer service's costs and improve its self-service capabilities. However, the description of questions is often ambigu-ous, and the operation and maintenance of online KG based QA services in-troduces a high cost. To address the above issues, this paper proposes a se-mantic enhancement based dynamic construction of domain knowledge graph for answering questions. We first employ a model combining LSTM and CRF to identify entities, and then propose a semantic enhancement method based on topic comparison to introduce external knowledge. We employ heuristic rules to get optimal answers, and then periodically update the global KG according to the integer linear programming solver's results. Our approach can achieve a high precise answering results with a low re-sponse delay by accurately recognizing entities, automatically mapping do-main knowledge to the KG, and online updating the KG. The experimental results show that our approach compared with the traditional method im-proves the precision, recall and F-measure by 6.41%, 16.46% and 11.17%, respectively.
Authors: Yao Sun (Nanjing Institute of Big Date, Jinling Institute of Technology, China); Lun Meng (Hohai University, China); Yan Zhang (Jinling Institute Of Technology, China)
Email: myresearch2020@126.com, studyscholar@foxmail.com, zy@jit.edu.cn