@inproceedings{singh-etal-2021-drag,
title = "{DRAG}: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting",
author = "Singh, Hrituraj and
Verma, Gaurav and
Garimella, Aparna and
Srinivasan, Balaji Vasan",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.73",
doi = "10.18653/v1/2021.eacl-main.73",
pages = "863--873",
abstract = "Author stylized rewriting is the task of rewriting an input text in a particular author{'}s style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate author stylized text without relying on a parallel corpus of data. However, these approaches are limited by the lack of explicit control of target attributes and being entirely data-driven. In this paper, we propose a Director-Generator framework to rewrite content in the target author{'}s style, specifically focusing on certain target attributes. We show that our proposed framework works well even with a limited-sized target author corpus. Our experiments on corpora consisting of relatively small-sized text authored by three distinct authors show significant improvements upon existing works to rewrite input texts in target author{'}s style. Our quantitative and qualitative analyses further show that our model has better meaning retention and results in more fluent generations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2021-drag">
<titleInfo>
<title>DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hrituraj</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balaji</namePart>
<namePart type="given">Vasan</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Author stylized rewriting is the task of rewriting an input text in a particular author’s style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate author stylized text without relying on a parallel corpus of data. However, these approaches are limited by the lack of explicit control of target attributes and being entirely data-driven. In this paper, we propose a Director-Generator framework to rewrite content in the target author’s style, specifically focusing on certain target attributes. We show that our proposed framework works well even with a limited-sized target author corpus. Our experiments on corpora consisting of relatively small-sized text authored by three distinct authors show significant improvements upon existing works to rewrite input texts in target author’s style. Our quantitative and qualitative analyses further show that our model has better meaning retention and results in more fluent generations.</abstract>
<identifier type="citekey">singh-etal-2021-drag</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.73</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.73</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>863</start>
<end>873</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting
%A Singh, Hrituraj
%A Verma, Gaurav
%A Garimella, Aparna
%A Srinivasan, Balaji Vasan
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Online
%F singh-etal-2021-drag
%X Author stylized rewriting is the task of rewriting an input text in a particular author’s style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate author stylized text without relying on a parallel corpus of data. However, these approaches are limited by the lack of explicit control of target attributes and being entirely data-driven. In this paper, we propose a Director-Generator framework to rewrite content in the target author’s style, specifically focusing on certain target attributes. We show that our proposed framework works well even with a limited-sized target author corpus. Our experiments on corpora consisting of relatively small-sized text authored by three distinct authors show significant improvements upon existing works to rewrite input texts in target author’s style. Our quantitative and qualitative analyses further show that our model has better meaning retention and results in more fluent generations.
%R 10.18653/v1/2021.eacl-main.73
%U https://aclanthology.org/2021.eacl-main.73
%U https://doi.org/10.18653/v1/2021.eacl-main.73
%P 863-873
Markdown (Informal)
[DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting](https://aclanthology.org/2021.eacl-main.73) (Singh et al., EACL 2021)
ACL