Please use this identifier to cite or link to this item:
Title: Semantic Graphs for Generating Deep Questions
Authors: Liangming Pan
Yuxi Xie
Yansong Feng
Tat Seng Chua 
Min-Yen Kan 
Issue Date: 2020
Publisher: Association for Computational Linguistics
Citation: Liangming Pan, Yuxi Xie, Yansong Feng, Tat Seng Chua, Min-Yen Kan (2020). Semantic Graphs for Generating Deep Questions. Proceedings of the 2020 Annual Meeting of the Association of Computational Linguistics (ACL '20) : 1463-1475. ScholarBank@NUS Repository.
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 of the input passage. In order to capture the global structure of the document and facilitate reasoning, we propose a novel framework which first constructs a semantic-level graph for the input document and then encodes the semantic graph by introducing an attention-based GGNN (Att-GGNN). Afterwards, we fuse the document-level and graphlevel 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-theart performance. The code is publicly available at SG-Deep-Question-Generation.
Source Title: Proceedings of the 2020 Annual Meeting of the Association of Computational Linguistics (ACL '20)
DOI: 10.18653/v1/2020.acl-main.135
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Semantic Graphs for Generating Deep Questions_ACL 2020_Camera Ready.pdf2.31 MBAdobe PDF



Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.