Iterative GNN-based Decoder for Question Generation

Zichu Fei, Qi Zhang, Yaqian Zhou


Abstract
Natural question generation (QG) aims to generate questions from a passage, and generated questions are answered from the passage. Most models with state-of-the-art performance model the previously generated text at each decoding step. However, (1) they ignore the rich structure information that is hidden in the previously generated text. (2) they ignore the impact of copied words on the passage. We perceive that information in previously generated words serves as auxiliary information in subsequent generation. To address these problems, we design the Iterative Graph Network-based Decoder (IGND) to model the previous generation using a Graph Neural Network at each decoding step. Moreover, our graph model captures dependency relations in the passage that boost the generation. Experimental results demonstrate that our model outperforms the state-of-the-art models with sentence-level QG tasks on SQuAD and MARCO datasets.
Anthology ID:
2021.emnlp-main.201
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2573–2582
Language:
URL:
https://aclanthology.org/2021.emnlp-main.201
DOI:
10.18653/v1/2021.emnlp-main.201
Bibkey:
Cite (ACL):
Zichu Fei, Qi Zhang, and Yaqian Zhou. 2021. Iterative GNN-based Decoder for Question Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2573–2582, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Iterative GNN-based Decoder for Question Generation (Fei et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.201.pdf
Video:
 https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.201.mp4
Code
 sion-zcfei/ignd
Data
MS MARCOSQuAD