Semantic Graphs for Generating Deep Questions

Abstract

This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information about the input passage. In order to capture the global structure of the document and facilitate reasoning, we propose a novel framework that first constructs a semantic-level graph for the input document and then encodes the semantic graph by introducing an attention-based GGNN (Att-GGNN). Afterward, we fuse the document-level and graph-level representations to perform joint training of content selection and question decoding. On the HotpotQA deep-question centric dataset, our model greatly improves performance over questions requiring reasoning over multiple facts, leading to state-of-the-art performance. The code is publicly available at r̆lhttps://github.com/WING-NUS/SG-Deep-Question-Generation.

Publication
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Liangming Pan
Doctoral Alumni (‘22)

Doctoral Alumni (‘22)

Yuxi Xie
Yuxi Xie
Doctoral Student (Jan ‘21)

PhD Candidate January 2021 Intake

Min-Yen Kan
Min-Yen Kan
Associate Professor

WING lead; interests include Digital Libraries, Information Retrieval and Natural Language Processing.