Knowledge Extraction Experiment Based on Tourism Knowledge Graph Q & A Data Set

At present, the most natural language processing tasks use common data sets for experiments. However, as the concept of domain knowledge graphs is proposed, domain-based data sets have gradually become a demand. In this article, we collect data from various travel websites and official websites of tourist attractions, and use this to build a question and answer data set. At the same time, we also introduce the current Bert model with outstanding effect in the nlp field, and use this model to conduct experiments in the travelling question and answer data set. The experimental results not only show the feasibility of the constructed tourism data set, but also lay a foundation for the subsequent construction of a knowledge question answering system for tourism knowledge graph.