# Adversarial Decomposition of Text Representation

arXiv: https://arxiv.org/abs/1808.09042 · HTML: https://mlsanity.com/paper/1808.09042/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 18 of 18)

- [Continual Learning for Text Classification with Information Disentanglement Based Regularization](https://mlsanity.com/paper/2104.05489/) (2021)
- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs](https://mlsanity.com/paper/2406.16797/) (2024)
- [Scalable Language Model with Generalized Continual Learning](https://mlsanity.com/paper/2404.07470/) (2024)
- [Attribute Alignment: Controlling Text Generation from Pre-trained Language Models](https://mlsanity.com/paper/2103.11070/) (2021)
- [Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding](https://mlsanity.com/paper/2109.11708/) (2021)
- [Self-conditioning pre-trained language models](https://mlsanity.com/paper/2110.02802/) (2021)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Task-Agnostic Low-Rank Adapters for Unseen English Dialects](https://mlsanity.com/paper/2311.00915/) (2023)
- [Advancements in Scientific Controllable Text Generation Methods](https://mlsanity.com/paper/2307.05538/) (2023)
- [Controlling Text Edition by Changing Answers of Specific Questions](https://mlsanity.com/paper/2105.11018/) (2021)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging](https://mlsanity.com/paper/2510.20479/) (2025)
- [Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining](https://mlsanity.com/paper/2104.07642/) (2021)
- [BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification](https://mlsanity.com/paper/2311.16083/) (2023)
- [Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation](https://mlsanity.com/paper/2202.13363/) (2022)
- [Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models](https://mlsanity.com/paper/2402.02145/) (2024)
- [Unsupervised Text Style Transfer with Deep Generative Models](https://mlsanity.com/paper/2308.16584/) (2023)

## Abstract (arXiv)

In this paper, we present a method for adversarial decomposition of text representation. This method can be used to decompose a representation of an input sentence into several independent vectors, each of them responsible for a specific aspect of the input sentence. We evaluate the proposed method on two case studies: the conversion between different social registers and diachronic language change. We show that the proposed method is capable of fine-grained controlled change of these aspects of the input sentence. It is also learning a continuous (rather than categorical) representation of the style of the sentence, which is more linguistically realistic. The model uses adversarial-motivational training and includes a special motivational loss, which acts opposite to the discriminator and encourages a better decomposition. Furthermore, we evaluate the obtained meaning embeddings on a downstream task of paraphrase detection and show that they significantly outperform the embeddings of a regular autoencoder.