Graph-Based Knowledge Integration for Question Answering over Dialogue

Jian Liu, Dianbo Sui, Kang Liu, Jun Zhao


Abstract
Question answering over dialogue, a specialized machine reading comprehension task, aims to comprehend a dialogue and to answer specific questions. Despite many advances, existing approaches for this task did not consider dialogue structure and background knowledge (e.g., relationships between speakers). In this paper, we introduce a new approach for the task, featured by its novelty in structuring dialogue and integrating background knowledge for reasoning. Specifically, different from previous “structure-less” approaches, our method organizes a dialogue as a “relational graph”, using edges to represent relationships between entities. To encode this relational graph, we devise a relational graph convolutional network (R-GCN), which can traverse the graph’s topological structure and effectively encode multi-relational knowledge for reasoning. The extensive experiments have justified the effectiveness of our approach over competitive baselines. Moreover, a deeper analysis shows that our model is better at tackling complex questions requiring relational reasoning and defending adversarial attacks with distracting sentences.
Anthology ID:
2020.coling-main.219
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2425–2435
Language:
URL:
https://aclanthology.org/2020.coling-main.219
DOI:
10.18653/v1/2020.coling-main.219
Bibkey:
Cite (ACL):
Jian Liu, Dianbo Sui, Kang Liu, and Jun Zhao. 2020. Graph-Based Knowledge Integration for Question Answering over Dialogue. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2425–2435, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Graph-Based Knowledge Integration for Question Answering over Dialogue (Liu et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.219.pdf