TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Horvitz, Zachary, Patel, Ajay, Singh, Kanishk, Callison-Burch, Chris, McKeown, Kathleen, Yu, Zhou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913573425381376
author Horvitz, Zachary
Patel, Ajay
Singh, Kanishk
Callison-Burch, Chris
McKeown, Kathleen
Yu, Zhou
author_facet Horvitz, Zachary
Patel, Ajay
Singh, Kanishk
Callison-Burch, Chris
McKeown, Kathleen
Yu, Zhou
contents 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. Our model has been made publicly available at https://huggingface.co/tinystyler/tinystyler .
format Preprint
id arxiv_https___arxiv_org_abs_2406_15586
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
Horvitz, Zachary
Patel, Ajay
Singh, Kanishk
Callison-Burch, Chris
McKeown, Kathleen
Yu, Zhou
Computation and Language
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. Our model has been made publicly available at https://huggingface.co/tinystyler/tinystyler .
title TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
topic Computation and Language
url https://arxiv.org/abs/2406.15586