paper-with-me

홈 › Papers

Rethinking Style Transformer by Energy-based Interpretation: Adversarial Unsupervised Style Transfer using Pretrained Model

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Style control, content preservation, and fluency determine the quality of text style transfer models. To train on a nonparallel corpus, several existing approaches aim to deceive the style discriminator with an adversarial loss. However, adversarial training significantly degrades fluency compared to the other two metrics. In this work, we explain this phenomenon with the energy-based interpretation and leverage a pretrained language model to improve fluency. Specifically, we propose a novel approach of applying the pretrained language model to the text style transfer framework by restructuring the discriminator and the model itself, allowing the generator and the discriminator to also take advantage of the power of the pretrained model. We evaluate our model on four public benchmarks Amazon, Yelp, GYAFC, and Civil Comments and achieve state-of-the-art performance on the overall metrics.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingStyle TransferText Style Transfer

Similar Papers 제목 키워드 기반

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack

2025-07-18 · Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo, Hyoungshick Kim 외 arxiv

Vision transformer (ViT) models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous …

Autonomous Vehicles

Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics

2026-04-09 · Raphael Bernas, Fanny Jourdan, Antonin Poché, Céline Hudelot arxiv

Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in these models, presenting a significant c…

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models

2024-08-27 · Xiyu Liu, Zhengxiao Liu, Naibin Gu, Zheng Lin 외

The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights. Most …

knowledge editingRelationSpecificity

YuriiFormer: A Suite of Nesterov-Accelerated Transformers

2026-01-30 · Aleksandr Zimin, Yury Polyanskiy, Philippe Rigollet arxiv

We propose a variational framework that interprets transformer layers as iterations of an optimization algorithm acting on token embeddings. In this view, self-attention implements a gradient step of an interaction energ…

Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer

2019-04-04 · Xinyuan Chen, Chang Xu, Xiaokang Yang, Li Song 외

Style transfer describes the rendering of an image semantic content as different artistic styles. Recently, generative adversarial networks (GANs) have emerged as an effective approach in style transfer by adversarially …

DecoderStyle Transfer