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

Priyanka Sen, Armin Oliya, Amir Saffari


Abstract
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.
Anthology ID:
2021.emnlp-main.694
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8805–8812
Language:
URL:
https://aclanthology.org/2021.emnlp-main.694
DOI:
10.18653/v1/2021.emnlp-main.694
Bibkey:
Cite (ACL):
Priyanka Sen, Armin Oliya, and Amir Saffari. 2021. Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8805–8812, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection (Sen et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.694.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.694.mp4
Data
ComplexWebQuestionsWebQuestionsSP