mlsanityData to 7 Oct 2026

Multi-Pair Text Style Transfer on Unbalanced Data

arXiv 2106.10608 ↗First posted 20 Jun 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel training data, as it is frequently the case there are multiple data sources of unequal size, with a mixture of labeled and unlabeled sentences. Moreover, the inherent style defined within each source might be distinct. A generic bidirectional (e.g., formal Leftrightarrow informal) style transfer regardless of different groups may not generalize well to different applications. In this work, we developed a task adaptive meta-learning framework that can simultaneously perform a multi-pair text-style transfer using a single model. The proposed method can adaptively balance the difference of meta-knowledge across multiple tasks. Results show that our method leads to better quantitative performance as well as coherent style variations. Common challenges of unbalanced data and mismatched domains are handled well by this method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 20 Jun 2021.

Builds on

23 of 38 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  6. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  8. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  9. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  10. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  11. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  12. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
11 more
  1. 2017Demystifying Neural Style Transfercited by 152
  2. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  3. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  4. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  5. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  6. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  7. 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
  8. 2019Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Taskscited by 48
  9. 2016Preserving Color in Neural Artistic Style Transfercited by 20
  10. 2018Style Transfer as Unsupervised Machine Translationcited by 19
  11. 2020ST2: Small-data Text Style Transfer via Multi-task Meta-Learningcited by 3

Built on by

Not cited yet.