Challenge: Text style transfer requires a high-quality paired dataset and quality training data.
Approach: They propose to use a pseudo-parallel dataset to adjust the style distribution in training data to balance the style transfer model.
Outcome: The proposed model produces more effective control effects over multiple styles than an imbalanced or skewed one.

Similar Papers

Style Transfer with Multi-iteration Preference Optimization (2025.naacl-long)

Copied to clipboard

Challenge: Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization.
Approach: They propose to use a pseudo-parallel data generation method and a dynamic weighted reward aggregation method to improve upon established preference optimization techniques.
Outcome: The proposed model outperforms existing models on two commonly used text style transfer datasets and is compared with state-of-the-art models.
An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation (2020.coling-industry)

Copied to clipboard

Challenge: a limited amount of style data is needed for text style transfer, but there are no convincing methods for evaluating them.
Approach: They propose an efficient method for neutral-to-style transformation using the transformer framework.
Outcome: The proposed method can train neutral-to-style transformation models using large paraphrases and a small style transfer corpus.
Semi-supervised Text Style Transfer: Cross Projection in Latent Space (D19-1)

Copied to clipboard

Challenge: Text style transfer task has long suffered from the shortage of parallel data .
Approach: They propose a semi-supervised text style transfer model that combines parallel data with large-scale nonparallel data to train it.
Outcome: The proposed model can transfer a sentence of one style to another while retaining its original content meaning while preserving its original meaning.
Text Style Transfer for Bias Mitigation using Masked Language Modeling (2022.naacl-srw)

Copied to clipboard

Challenge: Various research findings have concluded that biased textual data has significant effects on target demographic groups.
Approach: They propose a text-style transfer model that can be trained on non-parallel data and be used to automatically mitigate bias in textual data.
Outcome: The proposed model improves on limitations of existing methods while maintaining good style transfer accuracy.
TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for text style transfer require style-labeled training data, but use only labeled data at inference time.
Approach: They propose a method that uses readily-available unlabeled text to train style transfer . they use a style vector to condition a decoder to perform style transfer using unlabelled text .
Outcome: The proposed method is competitive on sentiment transfer, even compared to models trained fully on labeled data.
Understanding the effects of language-specific class imbalance in multilingual fine-tuning (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods to fine-tune large language models have been developed to reduce the amount of resources needed to perform classification tasks.
Approach: They modify traditional class weighing approach to reduce imbalance by calculating class weights separately for each language.
Outcome: The proposed model improves performance and reduces the promotion of uninformative features.
Style versus Content: A distinction without a (learnable) difference? (2020.coling-main)

Copied to clipboard

Challenge: Textual style transfer assumes that it is possible to separate style from content . however, style transfer can provide insight into language more generally .
Approach: They propose to use sentiment transfer to examine whether style transfer is possible . they employ adversarial encoder-decoder networks to analyze style-related features .
Outcome: The proposed method combines style transfer with content preservation and fluency to show that style cannot be usefully separated from content within style transfer systems.
Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding (2021.acl-long)

Copied to clipboard

Challenge: a benchmark corpus of text in 15 different styles is used to study stylistic language . a similar benchmark is used for cross-style language understanding .
Approach: They propose a benchmark corpus that combines existing datasets and collects a new one for cross-style language understanding.
Outcome: The proposed benchmark corpus contains 15 different styles under four theoretical groupings: figurative, personal, affective, and interpersonal groups.
Towards Actual (Not Operational) Textual Style Transfer Auto-Evaluation (D19-55)

Copied to clipboard

Challenge: elucidates the dangerous current state of style transfer auto-evaluation research.
Approach: They propose ways to aggregate the three metrics into one evaluator.
Outcome: The proposed method could be used to aggregate the three metrics into one evaluator.
Towards Modeling the Style of Translators in Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: a key ingredient of neural machine translation is the use of large datasets with different but consistent translation styles . however, the models do not capture the variety of translators' styles from the data . a recent study shows that style-augmented models can capture the style variations of translator .
Approach: They propose to augment a neural machine translation model with translator information . they use TED talk datasets to model and control translator-related stylistic variations .
Outcome: The proposed models capture the style variations of translators and generate translations with different styles on new data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations