Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection

09/13/2021

∙

by   Priyanka Sen, et al.

∙

0

∙

share

End-to-end question answering using a differentiable knowledge graph is a promising technique that requires only weak supervision, produces interpretable results, and is fully differentiable. Previous implementations of this technique (Cohen et al., 2020) have focused on single-entity questions using a relation following operation. In this paper, we propose a model that explicitly handles multiple-entity questions by implementing a new intersection operation, which identifies the shared elements between two sets of entities. We find that introducing intersection improves performance over a baseline model on two datasets, WebQuestionsSP (69.6 to 48.7 multiple entities by over 14 ComplexWebQuestions.