TY - GEN
T1 - Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing
AU - Huang, Qingbao
AU - Fu, Mingyi
AU - Mo, Linzhang
AU - Cai, Yi
AU - Xu, Jingyun
AU - Li, Pijian
AU - Li, Qing
AU - Leung, Ho Fung
N1 - Funding Information:
This work was supported by National Natural Science Foundation of China (62076100, 51767005), the National Key Research and Development Program of China, and the collaborative research grants from the Fundamental Research Funds for the Central Universities, SCUT (No. D2182480), the Science and Technology Planning Project of Guangdong Province (No.2017B050506004), the Science and Technology Programs of Guangzhou (No.201704030076, 201707010223, 201802010027, 201902010046), and the Hong Kong Research Grants Council, China (project no. PolyU1121417 and project no. C1031-18G), and an internal research grant from the Hong Kong Polytechnic University, China (project 1.9B0V).
Publisher Copyright:
© 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2021
Y1 - 2021
N2 - Question generation is a challenging task and has attracted widespread attention in recent years. Although previous studies have made great progress, there are still two main shortcomings: First, previous work did not simultaneously capture the sequence information and structure information hidden in the context, which results in poor results of the generated questions. Second, the generated questions cannot be answered by the given context. To tackle these issues, we propose an entity guided question generation model with contextual structure information and sequence information capturing. We use a Graph Convolutional Network and a Bidirectional Long Short Term Memory Network to capture the structure information and sequence information of the context, simultaneously. In addition, to improve the answerability of the generated questions, we use an entity-guided approach to obtain question type from the answer, and jointly encode the answer and question type. Both automatic and manual metrics show that our model can generate comparable questions with state-of-the-art models. Our code is available at https://github.com/VISLANG-Lab/EGSS.
AB - Question generation is a challenging task and has attracted widespread attention in recent years. Although previous studies have made great progress, there are still two main shortcomings: First, previous work did not simultaneously capture the sequence information and structure information hidden in the context, which results in poor results of the generated questions. Second, the generated questions cannot be answered by the given context. To tackle these issues, we propose an entity guided question generation model with contextual structure information and sequence information capturing. We use a Graph Convolutional Network and a Bidirectional Long Short Term Memory Network to capture the structure information and sequence information of the context, simultaneously. In addition, to improve the answerability of the generated questions, we use an entity-guided approach to obtain question type from the answer, and jointly encode the answer and question type. Both automatic and manual metrics show that our model can generate comparable questions with state-of-the-art models. Our code is available at https://github.com/VISLANG-Lab/EGSS.
UR - http://www.scopus.com/inward/record.url?scp=85123646467&partnerID=8YFLogxK
M3 - Conference article published in proceeding or book
AN - SCOPUS:85123646467
T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
SP - 13064
EP - 13072
BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
PB - Association for the Advancement of Artificial Intelligence
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
Y2 - 2 February 2021 through 9 February 2021
ER -