# Adversarial Text Generation via Feature-Mover's Distance

arXiv: https://arxiv.org/abs/1809.06297 · HTML: https://mlsanity.com/paper/1809.06297/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 27 of 27)

- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints](https://mlsanity.com/paper/2109.04546/) (2021)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [A survey on text generation using generative adversarial networks](https://mlsanity.com/paper/2212.11119/) (2022)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Learning quantum data with the quantum Earth Mover's distance](https://mlsanity.com/paper/2101.03037/) (2021)
- [A Survey of Natural Language Generation](https://mlsanity.com/paper/2112.11739/) (2021)
- [Political Depolarization of News Articles Using Attribute-aware Word Embeddings](https://mlsanity.com/paper/2101.01391/) (2021)
- [GeoPointGAN: Synthetic Spatial Data with Local Label Differential Privacy](https://mlsanity.com/paper/2205.08886/) (2022)
- [OTExtSum: Extractive Text Summarisation with Optimal Transport](https://mlsanity.com/paper/2204.10086/) (2022)
- [Improved Training of Mixture-of-Experts Language GANs](https://mlsanity.com/paper/2302.11875/) (2023)
- [Pattern Detection in the Activation Space for Identifying Synthesized Content](https://mlsanity.com/paper/2105.12479/) (2021)
- [Generating Symbolic Reasoning Problems with Transformer GANs](https://mlsanity.com/paper/2110.10054/) (2021)
- [Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification](https://mlsanity.com/paper/2203.01675/) (2022)
- [Text Style Transfer: An Introductory Overview](https://mlsanity.com/paper/2407.14822/) (2024)
- [Dangling-Aware Entity Alignment with Mixed High-Order Proximities](https://mlsanity.com/paper/2205.02406/) (2022)
- [Nested-Wasserstein Self-Imitation Learning for Sequence Generation](https://mlsanity.com/paper/2001.06944/) (2020)
- [Syntax Matters! Syntax-Controlled in Text Style Transfer](https://mlsanity.com/paper/2108.05869/) (2021)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases](https://mlsanity.com/paper/2203.05744/) (2022)
- [Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer](https://mlsanity.com/paper/2305.05945/) (2023)
- [Text Generation with Deep Variational GAN](https://mlsanity.com/paper/2104.13488/) (2021)
- [A hybrid data driven-physics constrained Gaussian process regression framework with deep kernel for uncertainty quantification](https://mlsanity.com/paper/2205.06494/) (2022)
- [InitialGAN: A Language GAN with Completely Random Initialization](https://mlsanity.com/paper/2208.02531/) (2022)
- [A Mutation-based Text Generation for Adversarial Machine Learning Applications](https://mlsanity.com/paper/2212.11808/) (2022)
- [Generative Sentiment Transfer via Adaptive Masking](https://mlsanity.com/paper/2302.12045/) (2023)
- [Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis](https://mlsanity.com/paper/2306.17181/) (2023)

## Abstract (arXiv)

Generative adversarial networks (GANs) have achieved significant success in generating real-valued data. However, the discrete nature of text hinders the application of GAN to text-generation tasks. Instead of using the standard GAN objective, we propose to improve text-generation GAN via a novel approach inspired by optimal transport. Specifically, we consider matching the latent feature distributions of real and synthetic sentences using a novel metric, termed the feature-mover's distance (FMD). This formulation leads to a highly discriminative critic and easy-to-optimize objective, overcoming the mode-collapsing and brittle-training problems in existing methods. Extensive experiments are conducted on a variety of tasks to evaluate the proposed model empirically, including unconditional text generation, style transfer from non-parallel text, and unsupervised cipher cracking. The proposed model yields superior performance, demonstrating wide applicability and effectiveness.