@inproceedings{jangra-etal-2022-star,
title = "{T}-{STAR}: Truthful Style Transfer using {AMR} Graph as Intermediate Representation",
author = "Jangra, Anubhav and
Nema, Preksha and
Raghuveer, Aravindan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.602",
doi = "10.18653/v1/2022.emnlp-main.602",
pages = "8805--8825",
abstract = "Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2{\%} higher content preservation with negligible loss ({\textasciitilde}3{\%}) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has upto 50{\%} lesser hallucinations compared to state of the art TST models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jangra-etal-2022-star">
<titleInfo>
<title>T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anubhav</namePart>
<namePart type="family">Jangra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preksha</namePart>
<namePart type="family">Nema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aravindan</namePart>
<namePart type="family">Raghuveer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2% higher content preservation with negligible loss (~3%) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has upto 50% lesser hallucinations compared to state of the art TST models.</abstract>
<identifier type="citekey">jangra-etal-2022-star</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.602</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.602</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8805</start>
<end>8825</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
%A Jangra, Anubhav
%A Nema, Preksha
%A Raghuveer, Aravindan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F jangra-etal-2022-star
%X Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2% higher content preservation with negligible loss (~3%) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has upto 50% lesser hallucinations compared to state of the art TST models.
%R 10.18653/v1/2022.emnlp-main.602
%U https://aclanthology.org/2022.emnlp-main.602
%U https://doi.org/10.18653/v1/2022.emnlp-main.602
%P 8805-8825
Markdown (Informal)
[T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation](https://aclanthology.org/2022.emnlp-main.602) (Jangra et al., EMNLP 2022)
ACL