@inproceedings{gu-etal-2019-extract,
title = "Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template",
author = "Gu, Yunfan and
Yuqiao, Yang and
Wei, Zhongyu",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5514",
doi = "10.18653/v1/D19-5514",
pages = "109--114",
abstract = "Question paraphrasing aims to restate a given question with different expressions but keep the original meaning. Recent approaches are mostly based on neural networks following a sequence-to-sequence fashion, however, these models tend to generate unpredictable results. To overcome this drawback, we propose a pipeline model based on templates. It follows three steps, a) identifies template from the input question, b) retrieves candidate templates, c) fills candidate templates with original topic words. Experiment results on two self-constructed datasets show that our model outperforms the sequence-to-sequence model in a large margin and the advantage is more promising when the size of training sample is small.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2019-extract">
<titleInfo>
<title>Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunfan</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yuqiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Question paraphrasing aims to restate a given question with different expressions but keep the original meaning. Recent approaches are mostly based on neural networks following a sequence-to-sequence fashion, however, these models tend to generate unpredictable results. To overcome this drawback, we propose a pipeline model based on templates. It follows three steps, a) identifies template from the input question, b) retrieves candidate templates, c) fills candidate templates with original topic words. Experiment results on two self-constructed datasets show that our model outperforms the sequence-to-sequence model in a large margin and the advantage is more promising when the size of training sample is small.</abstract>
<identifier type="citekey">gu-etal-2019-extract</identifier>
<identifier type="doi">10.18653/v1/D19-5514</identifier>
<location>
<url>https://aclanthology.org/D19-5514</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>109</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template
%A Gu, Yunfan
%A Yuqiao, Yang
%A Wei, Zhongyu
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F gu-etal-2019-extract
%X Question paraphrasing aims to restate a given question with different expressions but keep the original meaning. Recent approaches are mostly based on neural networks following a sequence-to-sequence fashion, however, these models tend to generate unpredictable results. To overcome this drawback, we propose a pipeline model based on templates. It follows three steps, a) identifies template from the input question, b) retrieves candidate templates, c) fills candidate templates with original topic words. Experiment results on two self-constructed datasets show that our model outperforms the sequence-to-sequence model in a large margin and the advantage is more promising when the size of training sample is small.
%R 10.18653/v1/D19-5514
%U https://aclanthology.org/D19-5514
%U https://doi.org/10.18653/v1/D19-5514
%P 109-114
Markdown (Informal)
[Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template](https://aclanthology.org/D19-5514) (Gu et al., WNUT 2019)
ACL