Effective Search of Logical Forms in Question Answering based on the Knowledge Graph using Logical Form Patterns

Abstract

CSQA is a question answering benchmark using the knowledge graph, that created using the large-scale knowledge graph database Wikidata. CSQA targets interactive question answering, and there are 10 question types, some of which require inference such as comparison and set operation. In the previous study, multi-task semantic parsing model that converts utterances to logical forms that expresses operations on a database can answer high accuracy. The conversion to a logical form is performed by defining the grammar for deriving the logical form and predicting the order in which the grammar is applied from the utterance. In order to learn a model for the prediction, it is necessary to search for a logical form that can answer the question from logical forms that can be generated by applying the grammar. However, since the search space is enormous, depending on the search method, problems such as a decrease in the success rate of the search and incorrect logical forms occur, which may adversely affect the learning of the model. In this research, we propose a method for searching logical forms with a high success rate of the search in a short time by using patterns of logical forms.