%0 Conference Proceedings %T Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection %A Sen, Priyanka %A Oliya, Armin %A Saffari, Amir %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F sen-etal-2021-expanding %X 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 73.3% Hits@1) and ComplexWebQuestions (39.8% to 48.7% Hits@1), and in particular, improves performance on questions with multiple entities by over 14% on WebQuestionsSP and by 19% on ComplexWebQuestions. %R 10.18653/v1/2021.emnlp-main.694 %U https://aclanthology.org/2021.emnlp-main.694 %U https://doi.org/10.18653/v1/2021.emnlp-main.694 %P 8805-8812