Knowledge base question answering requires a large number of question answering pairs when relying on the knowledge base to infer answers.However,building a large-scale and accurate data set is not only expensive,but also limited by factors such as domain.To alleviate the problem of data labeling,the question generation from knowledge base has attracted the attention of researchers.This task is to use the triples of knowledge base to automatically generate the questions.However,existing methods only use a triple to generate questions that are short and lack diversity.To generate questions with rich and diverse information,this paper use two encoding layers,Graph Transformer and BERT,to enhance the multi-granular semantic representation of triples to obtain background information.Experimental results on the SimpleQuestions dataset prove the effectiveness of the method.
问题生成知识库语义表征知识库问答
胡月、周光有
展开 >
华中师范大学计算机学院 湖北武汉
问题生成 知识库 语义表征 知识库问答
Chinese National Conference on Computational Linguistic
Haikou(CN)
19th Chinese National Conference on Computational Linguistic
NETL
