paper-with-me

홈 › Papers

Text Style Transfer: A Review and Experimental Evaluation

2020-10-24 · Zhiqiang Hu, Roy Ka-Wei Lee, Charu C. Aggarwal, Aston Zhang

The stylistic properties of text have intrigued computational linguistics researchers in recent years. Specifically, researchers have investigated the Text Style Transfer (TST) task, which aims to change the stylistic properties of the text while retaining its style independent content. Over the last few years, many novel TST algorithms have been developed, while the industry has leveraged these algorithms to enable exciting TST applications. The field of TST research has burgeoned because of this symbiosis. This article aims to provide a comprehensive review of recent research efforts on text style transfer. More concretely, we create a taxonomy to organize the TST models and provide a comprehensive summary of the state of the art. We review the existing evaluation methodologies for TST tasks and conduct a large-scale reproducibility study where we experimentally benchmark 19 state-of-the-art TST algorithms on two publicly available datasets. Finally, we expand on current trends and provide new perspectives on the new and exciting developments in the TST field.

📄 PDF Abstract BibTeX arXiv:2010.12742

Code (2)

RemiArbache/style-transfer-M2 tf
fuzhenxin/Style-Transfer-in-Text pytorch

Tasks

Style TransferText Style Transfer

Similar Papers 제목 키워드 기반

A Review of Human Evaluation for Style Transfer

2021-06-09 · ACL (GEM) 2021 8 · Eleftheria Briakou, Sweta Agrawal, Ke Zhang, Joel Tetreault 외

This paper reviews and summarizes human evaluation practices described in 97 style transfer papers with respect to three main evaluation aspects: style transfer, meaning preservation, and fluency. In principle, evaluatio…

Style Transfer

Style Transfer in Text: Exploration and Evaluation

2017-11-18 · Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao 외

Style transfer is an important problem in natural language processing (NLP). However, the progress in language style transfer is lagged behind other domains, such as computer vision, mainly because of the lack of paralle…

Style TransferText Style Transfer

Review of Text Style Transfer Based on Deep Learning

2020-05-06 · Xiang-Yang Li, Guo Pu, Keyu Ming, Pu Li 외

Text style transfer is a hot issue in recent natural language processing,which mainly studies the text to adapt to different specific situations, audiences and purposes by making some changes. The style of the text usual…

Deep LearningStyle TransferText Style Transfer

A Review of Text Style Transfer using Deep Learning

2021-09-30 · Martina Toshevska, Sonja Gievska

Style is an integral component of a sentence indicated by the choice of words a person makes. Different people have different ways of expressing themselves, however, they adjust their speaking and writing style to a soci…

Deep LearningNatural Language UnderstandingRepresentation LearningSentence+2

Evaluating Style Transfer for Text

2019-04-04 · NAACL 2019 6 · Remi Mir, Bjarke Felbo, Nick Obradovich, Iyad Rahwan

Research in the area of style transfer for text is currently bottlenecked by a lack of standard evaluation practices. This paper aims to alleviate this issue by experimentally identifying best practices with a Yelp senti…

Style Transfer