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

arXiv: https://arxiv.org/abs/2205.02309 · HTML: https://mlsanity.com/paper/2205.02309/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 4 May 2022.

## Builds on (most cited first, 25 of 25)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Dialogue Natural Language Inference](https://mlsanity.com/paper/1811.00671/) (2018)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [Unsupervised Text Style Transfer using Language Models as Discriminators](https://mlsanity.com/paper/1805.11749/) (2018)
- [Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation](https://mlsanity.com/paper/1706.09799/) (2017)
- [Evaluating Style Transfer for Text](https://mlsanity.com/paper/1904.02295/) (2019)
- [Generating Sentences from Disentangled Syntactic and Semantic Spaces](https://mlsanity.com/paper/1907.05789/) (2019)
- [TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling](https://mlsanity.com/paper/2010.03802/) (2020)
- [LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2105.08206/) (2021)
- [A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations](https://mlsanity.com/paper/1904.01173/) (2019)
- [StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer](https://mlsanity.com/paper/2104.05196/) (2021)
- [On the Latent Space of Wasserstein Auto-Encoders](https://mlsanity.com/paper/1802.03761/) (2018)
- [Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning](https://mlsanity.com/paper/1905.12304/) (2019)
- [Denoising Adversarial Autoencoders](https://mlsanity.com/paper/1703.01220/) (2017)
- [Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization](https://mlsanity.com/paper/2108.00449/) (2021)

## Built on by (most cited first, 7 of 7)

- [SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation](https://mlsanity.com/paper/2403.17768/) (2024)
- [Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation](https://mlsanity.com/paper/2305.00034/) (2023)
- [Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation](https://mlsanity.com/paper/2211.09455/) (2022)
- [LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following](https://mlsanity.com/paper/2308.04913/) (2023)
- [CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization](https://mlsanity.com/paper/2210.14190/) (2022)
- [Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets](https://mlsanity.com/paper/2403.20056/) (2024)
- [On Text Style Transfer via Style Masked Language Models](https://mlsanity.com/paper/2210.06394/) (2022)

## Abstract (arXiv)

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. The latent space geometry of such models is organised well enough to perform on datasets where the style is "coarse-grained" i.e. a small fraction of words alone in a sentence are enough to determine the overall style label. A recent study uses a discrete token-based perturbation approach to map "similar" sentences ("similar" defined by low Levenshtein distance/ high word overlap) close by in latent space. This definition of "similarity" does not look into the underlying nuances of the constituent words while mapping latent space neighbourhoods and therefore fails to recognise sentences with different style-based semantics while mapping latent neighbourhoods. We introduce EPAAEs (Embedding Perturbed Adversarial AutoEncoders) which completes this perturbation model, by adding a finely adjustable noise component on the continuous embeddings space. 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. We also extend the text style transfer tasks to NLI datasets and show that these more complex definitions of style are learned best by EPAAE. To the best of our knowledge, extending style transfer to NLI tasks has not been explored before.