Unsupervised Text Style Transfer
21 papers with code • 3 benchmarks • 3 datasets
Latest papers
MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
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.
Composable Text Controls in Latent Space with ODEs
This paper proposes a new efficient approach for composable text operations in the compact latent space of text.
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
RLPrompt formulates a parameter-efficient policy network that generates the desired discrete prompt after training with reward.
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
Automatic transfer of text between domains has become popular in recent times.
Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer
We empirically show that this (a) produces a better organised latent space that clusters stylistically similar sentences together, (b) performs best on a diverse set of text style transfer tasks than similar denoising-inspired baselines, and (c) is capable of fine-grained control of Style Transfer strength.
Transductive Learning for Unsupervised Text Style Transfer
The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Such training objective is sub-optimal when the target sequence is not perfect, e. g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available.
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
First, we observe that most words in the transferred sentence can be aligned with related words in the source sentence, so we explicitly model word alignments to suppress irrelevant words.
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer
Moreover, compared to previous methods on unsupervised data synthesis, our method results in higher quality parallel style pairs and improves model performance.
How Positive Are You: Text Style Transfer using Adaptive Style Embedding
In both approaches, however, it is impossible to adjust the strength of the style in the generated output.