Capturing Greater Context for Question Generation
Name
1910.10274.pdf
Description
Submitted version
Size
1.98 MB
Format
Adobe PDF
Checksum (MD5)
90a569d0bb499b93a2bd4f321a289dbb
Author(s)
Tuan, Luu Anh
Shah, Darsh J.(Darsh Jaidip)
Barzilay, Regina
Date Issued
April 2020
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Tuan, Luu Anh et al. "Capturing Greater Context for Question Generation." Proceedings of the AAAI Conference on Artificial Intelligence 34, 5 (April 2020): 9065-9072 © 2020 Association for the Advancement of Artificial Intelligence
Version
Original manuscript
Abstract
Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents. Many existing techniques generate questions by effectively looking at one sentence at a time, leading to questions that are easy and not reflective of the human process of question generation. Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. In order to link a broad document context to the target answer, we represent the relevant context via a multi-stage attention mechanism, which forms the foundation of a sequence to sequence model. We outperform state-of-the-art methods on question generation on three question-answering datasets - SQuAD, MS MARCO and NewsQA.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1609/aaai.v34i05.6440
