Graph-Based Knowledge Integration for Question Answering over Dialogue
Jian Liu, Dianbo Sui, Kang Liu, Jun Zhao · 2020
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.