@inproceedings{horvitz-etal-2024-tinystyler,
title = "{T}iny{S}tyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings",
author = "Horvitz, Zachary and
Patel, Ajay and
Singh, Kanishk and
Callison-Burch, Chris and
McKeown, Kathleen and
Yu, Zhou",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.781/",
doi = "10.18653/v1/2024.findings-emnlp.781",
pages = "13376--13390",
abstract = "The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of large language models or on complex controllable text generation approaches that are inefficient and underperform on fluency metrics. We introduce TinyStyler, a lightweight but effective approach, which leverages a small language model (800M params) and pre-trained authorship embeddings to perform efficient, few-shot text style transfer. We evaluate on the challenging task of authorship style transfer and find TinyStyler outperforms strong approaches such as GPT-4. We also evaluate TinyStyler`s ability to perform text attribute style transfer (formal $\leftrightarrow$ informal) with automatic and human evaluations and find that the approach outperforms recent controllable text generation methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horvitz-etal-2024-tinystyler">
<titleInfo>
<title>TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Horvitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajay</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanishk</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of large language models or on complex controllable text generation approaches that are inefficient and underperform on fluency metrics. We introduce TinyStyler, a lightweight but effective approach, which leverages a small language model (800M params) and pre-trained authorship embeddings to perform efficient, few-shot text style transfer. We evaluate on the challenging task of authorship style transfer and find TinyStyler outperforms strong approaches such as GPT-4. We also evaluate TinyStyler‘s ability to perform text attribute style transfer (formal łeftrightarrow informal) with automatic and human evaluations and find that the approach outperforms recent controllable text generation methods.</abstract>
<identifier type="citekey">horvitz-etal-2024-tinystyler</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.781</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.781/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>13376</start>
<end>13390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
%A Horvitz, Zachary
%A Patel, Ajay
%A Singh, Kanishk
%A Callison-Burch, Chris
%A McKeown, Kathleen
%A Yu, Zhou
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F horvitz-etal-2024-tinystyler
%X The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of large language models or on complex controllable text generation approaches that are inefficient and underperform on fluency metrics. We introduce TinyStyler, a lightweight but effective approach, which leverages a small language model (800M params) and pre-trained authorship embeddings to perform efficient, few-shot text style transfer. We evaluate on the challenging task of authorship style transfer and find TinyStyler outperforms strong approaches such as GPT-4. We also evaluate TinyStyler‘s ability to perform text attribute style transfer (formal łeftrightarrow informal) with automatic and human evaluations and find that the approach outperforms recent controllable text generation methods.
%R 10.18653/v1/2024.findings-emnlp.781
%U https://aclanthology.org/2024.findings-emnlp.781/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.781
%P 13376-13390
Markdown (Informal)
[TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings](https://aclanthology.org/2024.findings-emnlp.781/) (Horvitz et al., Findings 2024)
ACL