paper-with-me

홈 › Papers

Replacing Language Model for Style Transfer

2022-11-14 · Pengyu Cheng, Ruineng Li

We introduce replacing language model (RLM), a sequence-to-sequence language modeling framework for text style transfer (TST). Our method autoregressively replaces each token of the source sentence with a text span that has a similar meaning but in the target style. The new span is generated via a non-autoregressive masked language model, which can better preserve the local-contextual meaning of the replaced token. This RLM generation scheme gathers the flexibility of autoregressive models and the accuracy of non-autoregressive models, which bridges the gap between sentence-level and word-level style transfer methods. To control the generation style more precisely, we conduct a token-level style-content disentanglement on the hidden representations of RLM. Empirical results on real-world text datasets demonstrate the effectiveness of RLM compared with other TST baselines. The code is at https://github.com/Linear95/RLM.

📄 PDF Abstract BibTeX arXiv:2211.07343

Code (1)

linear95/rlm 공식 구현 pytorch

Tasks

DisentanglementLanguage ModelingLanguage ModellingmodelSentenceSequence-to-sequence Language ModelingStyle TransferText Style Transfer

Similar Papers 제목 키워드 기반

Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks

2018-07-06 · Cheng-Wei Wu, Jen-Yu Liu, Yi-Hsuan Yang, Jyh-Shing R. Jang

Can we make a famous rap singer like Eminem sing whatever our favorite song? Singing style transfer attempts to make this possible, by replacing the vocal of a song from the source singer to the target singer. This paper…

Style Transfer

Neural Neighbor Style Transfer

2022-03-24 · Nicholas Kolkin, Michal Kucera, Sylvain Paris, Daniel Sykora 외

We propose Neural Neighbor Style Transfer (NNST), a pipeline that offers state-of-the-art quality, generalization, and competitive efficiency for artistic style transfer. Our approach is based on explicitly replacing neu…

Style Transfer

An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation

2020-12-01 · COLING 2020 8 · Pawel Bujnowski, Kseniia Ryzhova, Hyungtak Choi, Katarzyna Witkowska 외

The topic of this paper is neural multi-task training for text style transfer. We present an efficient method for neutral-to-style transformation using the transformer framework. We demonstrate how to prepare a robust mo…

Multi-Task LearningParaphrase GenerationStyle TransferText Style Transfer

Data Augmentation Through Random Style Replacement

2025-04-14 · Qikai Yang, Cheng Ji, Huaiying Luo, Panfeng Li 외

In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach…

Data AugmentationStyle Transfer

An Interpretable X-ray Style Transfer via Trainable Local Laplacian Filter

2024-11-11 · Dominik Eckert, Ludwig Ritschl, Christopher Syben, Christian Hümmer 외

Radiologists have preferred visual impressions or 'styles' of X-ray images that are manually adjusted to their needs to support their diagnostic performance. In this work, we propose an automatic and interpretable X-ray …

DiagnosticSSIMStyle Transfer