@inproceedings{yuan-etal-2017-machine,
title = "Machine Comprehension by Text-to-Text Neural Question Generation",
author = "Yuan, Xingdi and
Wang, Tong and
Gulcehre, Caglar and
Sordoni, Alessandro and
Bachman, Philip and
Zhang, Saizheng and
Subramanian, Sandeep and
Trischler, Adam",
booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2603",
doi = "10.18653/v1/W17-2603",
pages = "15--25",
abstract = "We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2017-machine">
<titleInfo>
<title>Machine Comprehension by Text-to-Text Neural Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingdi</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caglar</namePart>
<namePart type="family">Gulcehre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Sordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Bachman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saizheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Trischler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.</abstract>
<identifier type="citekey">yuan-etal-2017-machine</identifier>
<identifier type="doi">10.18653/v1/W17-2603</identifier>
<location>
<url>https://aclanthology.org/W17-2603</url>
</location>
<part>
<date>2017-aug</date>
<extent unit="page">
<start>15</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Comprehension by Text-to-Text Neural Question Generation
%A Yuan, Xingdi
%A Wang, Tong
%A Gulcehre, Caglar
%A Sordoni, Alessandro
%A Bachman, Philip
%A Zhang, Saizheng
%A Subramanian, Sandeep
%A Trischler, Adam
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 aug
%I Association for Computational Linguistics
%C Vancouver, Canada
%F yuan-etal-2017-machine
%X We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.
%R 10.18653/v1/W17-2603
%U https://aclanthology.org/W17-2603
%U https://doi.org/10.18653/v1/W17-2603
%P 15-25
Markdown (Informal)
[Machine Comprehension by Text-to-Text Neural Question Generation](https://aclanthology.org/W17-2603) (Yuan et al., 2017)
ACL
- Xingdi Yuan, Tong Wang, Caglar Gulcehre, Alessandro Sordoni, Philip Bachman, Saizheng Zhang, Sandeep Subramanian, and Adam Trischler. 2017. Machine Comprehension by Text-to-Text Neural Question Generation. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 15–25, Vancouver, Canada. Association for Computational Linguistics.