paper-with-me

Papers Unsupervised Text Style Transfer

“Unsupervised Text Style Transfer” 태그가 달린 논문 42편 · 필터 해제

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL

2024-07-20 · Yunseon Choi, Sangmin Bae, Seonghyun Ban, Minchan Jeong 외

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords incl…

Few-Shot Text ClassificationQ-LearningReinforcement Learning (RL)Style Transfer+4

Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions

2024-02-21 · Lei Pan, Yunshi Lan, Yang Li, Weining Qian

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its…

In-Context LearningKnowledge DistillationSentenceStyle Transfer+2

Prefix-Tuning Based Unsupervised Text Style Transfer

2023-10-23 · Huiyu Mai, Wenhao Jiang, Zhihong Deng

Unsupervised text style transfer aims at training a generative model that can alter the style of the input sentence while preserving its content without using any parallel data. In this paper, we employ powerful pre-trai…

SentenceStyle TransferText Style TransferUnsupervised Text Style Transfer

Unsupervised Text Style Transfer with Deep Generative Models

2023-08-31 · Zhongtao Jiang, Yuanzhe Zhang, Yiming Ju, Kang Liu

We present a general framework for unsupervised text style transfer with deep generative models. The framework models each sentence-label pair in the non-parallel corpus as partially observed from a complete quadruplet w…

SentenceStyle TransferText Style TransferUnsupervised Text Style Transfer

MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer

2023-06-12 · Yazheng Yang, Zhou Zhao, Qi Liu

Unsupervised text style transfer task aims to rewrite a text into target style while preserving its main content. Traditional methods rely on the use of a fixed-sized vector to regulate text style, which is difficult to …

Style TransferText Style TransferUnsupervised Text Style Transfer

StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer

2022-12-19 · Kangchen Zhu, Zhiliang Tian, Ruifeng Luo, Xiaoguang Mao

Text style transfer aims to alter the style of a sentence while preserving its content. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and often uses cycle construction to train mod…

Data AugmentationDecoderDisentanglementSentence+3

Composable Text Controls in Latent Space with ODEs

2022-08-01 · Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang 외

Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and generating new text of desired properti…

AttributeLanguage ModelingLanguage ModellingText Style Transfer+1

Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

2022-07-01 · NAACL 2022 7 · Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang 외

Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a target sequence with a generated sequen…

Machine TranslationStyle TransferText GenerationText Style Transfer+1

Low Resource Style Transfer via Domain Adaptive Meta Learning

2022-05-25 · NAACL 2022 7 · Xiangyang Li, Xiang Long, Yu Xia, Sujian Li

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data t…

General KnowledgeLanguage ModelingLanguage ModellingMeta-Learning+3

RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning

2022-05-25 · Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang 외

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Style Transfer+2

So Different Yet So Alike! Constrained Unsupervised Text Style Transfer

2022-05-09 · ACL 2022 5 · Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann 외

Automatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content of text being translated from source to target domain. However, it does not explicitly ma…

AttributeData AugmentationGenerative Adversarial NetworkStyle Transfer+2

Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer

2022-05-04 · NAACL 2022 7 · Sharan Narasimhan, Suvodip Dey, Maunendra Sankar Desarkar

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. T…

DenoisingSentenceStyle TransferText Generation+2

Efficient Reinforcement Learning for Unsupervised Controlled Text Generation

2022-04-16 · Bhargav Upadhyay, Akhilesh Sudhakar, Arjun Maheswaran

Controlled text generation tasks such as unsupervised text style transfer have increasingly adopted the use of Reinforcement Learning (RL). A major challenge in applying RL to such tasks is the sparse reward, which is av…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Style Transfer+3

Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning

2022-01-23 · Chenghao Fan, Ziao Li, Wei Wei

Text style transfer is a challenging text generation problem, which aims at altering the style of a given sentence to a target one while keeping its content unchanged. Since there is a natural scarcity of parallel datase…

Adversarial AttackContrastive LearningSentenceStyle Transfer+3

Low Resource Style Transfer via Domain Adaptive Meta Learning

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

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of nonparallel data t…

General KnowledgeLanguage ModelingLanguage ModellingMeta-Learning+3

Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

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

Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a target sequence with a generated sequen…

Machine TranslationStyle TransferText GenerationText Style Transfer+1

DAML-ST5: Low Resource Style Transfer via Domain Adaptive Meta Learning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of nonparallel data to…

General KnowledgeLanguage ModelingLanguage ModellingMeta-Learning+3

Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer

2021-11-01 · EMNLP 2021 11 · Yun Ma, Yangbin Chen, Xudong Mao, Qing Li

Unsupervised text style transfer aims to alter the underlying style of the text to a desired value while keeping its style-independent semantics, without the support of parallel training corpora. Existing methods struggl…

AttributeDecoderKnowledge DistillationStyle Transfer+2

Exploring Non-Autoregressive Text Style Transfer

2021-11-01 · EMNLP 2021 11 · Yun Ma, Qing Li

In this paper, we explore Non-AutoRegressive (NAR) decoding for unsupervised text style transfer. We first propose a base NAR model by directly adapting the common training scheme from its AutoRegressive (AR) counterpart…

Contrastive LearningKnowledge DistillationStyle TransferText Style Transfer+1

Transductive Learning for Unsupervised Text Style Transfer

2021-09-16 · EMNLP 2021 11 · Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang 외

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to…

DecoderInductive LearningRetrievalStyle Transfer+3
1–20 / 42 다음 →