Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph
This addresses the issue of noisy query graph generation in complex KGQA, which is incremental as it builds on existing methods by incorporating semantic structure.
The paper tackles the problem of generating query graphs from natural language questions for knowledge graph question answering by predicting semantic structures to filter noisy candidates, achieving state-of-the-art results on benchmarks like MetaQA and WebQuestionsSP.
Building query graphs from natural language questions is an important step in complex question answering over knowledge graph (Complex KGQA). In general, a question can be correctly answered if its query graph is built correctly and the right answer is then retrieved by issuing the query graph against the KG. Therefore, this paper focuses on query graph generation from natural language questions. Existing approaches for query graph generation ignore the semantic structure of a question, resulting in a large number of noisy query graph candidates that undermine prediction accuracies. In this paper, we define six semantic structures from common questions in KGQA and develop a novel Structure-BERT to predict the semantic structure of a question. By doing so, we can first filter out noisy candidate query graphs, and then rank the remaining candidates with a BERT-based ranking model. Extensive experiments on two popular benchmarks MetaQA and WebQuestionsSP (WSP) demonstrate the effectiveness of our method as compared to state-of-the-arts.