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

09/13/2021
by   Priyanka Sen, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset