Text Style Transfer
2개 벤치마크 · 논문 199편 · 이 태스크의 논문 보기 →
Benchmarks
Yelp Review Dataset (Small)
Most implemented
Style Transfer from Non-Parallel Text by Cross-Alignment
A Probabilistic Formulation of Unsupervised Text Style Transfer
VAE based Text Style Transfer with Pivot Words Enhancement Learning
Papers
StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer
AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rests on a fundamental paradox: as language models are trained on human-…
Text Style TransferSemantic SimilarityContinuous ControlText Style Transfer with Machine Translation for Graphic Designs
Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs need…
Text Style TransferMachine TranslationWord AlignmentPlease Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer
AI-generated text has become common in academic and professional writing, prompting research into detection methods. Less studied is the reverse: systematically rewriting AI-generated prose to read as genuinely human-aut…
Text Style TransferText Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation
This paper proposes a novel method for Text Style Transfer (TST) based on parameter-efficient fine-tuning of Large Language Models (LLMs). Addressing the scarcity of parallel corpora that map between styles, the study em…
parameter-efficient fine-tuningText Style TransferText Detoxification in isiXhosa and Yorùbá: A Cross-Lingual Machine Learning Approach for Low-Resource African Languages
Toxic language is one of the major barrier to safe online participation, yet robust mitigation tools are scarce for African languages. This study addresses this critical gap by investigating automatic text detoxification…
Interpretable Machine LearningText Style TransferUnsupervised Text Style Transfer for Controllable Intensity
Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between style polarities, UTST for controllable…
Text Style Transfer