ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning

• URL: http://arxiv.org/abs/2004.11742v1
• Date: Fri, 24 Apr 2020 13:36:38 GMT
• Title: ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
• Authors: Xiwen Chen, Kenny Q. Zhu
• Abstract summary: Text style transfer aims to paraphrase a sentence in one style into another while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share content. In this work, we develop a meta-learning framework to transfer between any kind of text styles.
• Score: 14.271083093944753
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share content. Furthermore, existing methods have been applied on very limited categories of styles such as positive/negative and formal/informal. In this work, we develop a meta-learning framework to transfer between any kind of text styles, including personal writing styles that are more fine-grained, share less content and have much smaller training data. While state-of-art models fail in the few-shot style transfer task, our framework effectively utilizes information from other styles to improve both language fluency and style transfer accuracy.

Related papers

• Don't lose the message while paraphrasing: A study on content preserving style transfer [61.38460184163704]
  Content preservation is critical for real-world applications of style transfer studies. We compare various style transfer models on the example of the formality transfer domain. We conduct a precise comparative study of several state-of-the-art techniques for style transfer.
  arXiv  Detail & Related papers  (2023-08-17T15:41:08Z)
• MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer [82.37710853235535]
  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 accurately convey the style strength for each individual token. Our proposed method addresses this issue by assigning individual style vector to each token in a text, allowing for fine-grained control and manipulation of the style strength.
  arXiv  Detail & Related papers  (2023-06-12T13:12:29Z)
• StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model [64.26721402514957]
  We propose StylerDALLE, a style transfer method that uses natural language to describe abstract art styles. Specifically, we formulate the language-guided style transfer task as a non-autoregressive token sequence translation. To incorporate style information, we propose a Reinforcement Learning strategy with CLIP-based language supervision.
  arXiv  Detail & Related papers  (2023-03-16T12:44:44Z)
• Conversation Style Transfer using Few-Shot Learning [56.43383396058639]
  In this paper, we introduce conversation style transfer as a few-shot learning problem. We propose a novel in-context learning approach to solve the task with style-free dialogues as a pivot. We show that conversation style transfer can also benefit downstream tasks.
  arXiv  Detail & Related papers  (2023-02-16T15:27:00Z)
• StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing [73.81778485157234]
  Long texts usually involve more complicated author linguistic preferences such as discourse structures than sentences. We formulate the task of non-parallel story author-style transfer, which requires transferring an input story into a specified author style. We use an additional training objective to disentangle stylistic features from the learned discourse representation to prevent the model from degenerating to an auto-encoder.
  arXiv  Detail & Related papers  (2022-08-29T08:47:49Z)
• Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning [84.8813842101747]
  Contrastive Arbitrary Style Transfer (CAST) is a new style representation learning and style transfer method via contrastive learning. Our framework consists of three key components, i.e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer.
  arXiv  Detail & Related papers  (2022-05-19T13:11:24Z)
• StyleBabel: Artistic Style Tagging and Captioning [38.792350870518504]
  We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks.
  arXiv  Detail & Related papers  (2022-03-10T12:15:55Z)
• TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling [23.60231661500702]
  We present a novel approach to the problem of text style transfer. Our method makes use of readily-available unlabeled text by relying on the implicit connection in style between adjacent sentences. We demonstrate that training on unlabeled Amazon reviews data results in a model that is competitive on sentiment transfer.
  arXiv  Detail & Related papers  (2020-10-08T07:06:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.