Paragraph Level Multi-Perspective Context Modeling for Question Generation
Jun Bai, Wenge Rong, Feiyu Xia, Yanmeng Wang, Yuanxin Ouyang, Zhang Xiong
Abstract
Proper understanding of paragraph is essential for question generation task since the semantic interaction is complicated among sentences. How to integrate long text paragraph information into question generation is still a challenge. In this research, we proposed a multi-perspective paragraph context modeling mechanism, which firstly encodes the contextualized representation of input paragraph, and then utilize multi-head self-attention and Rezero network to further enhance paragraph-level feature extraction and context modeling. Finally, attention-based decoder with copy mechanism generates question according to encoded hidden states. Experimental study on widely used SQuAD dataset has shown the proposed method’s potential.
BibTeX
@inproceedings{icassp2021_paragraphlevelmu,
title = {Paragraph Level Multi-Perspective Context Modeling for Question Generation},
author = {Jun Bai and Wenge Rong and Feiyu Xia and Yanmeng Wang and Yuanxin Ouyang and Zhang Xiong},
booktitle = {ICASSP 2021},
year = {2021}
}