# Learning to Generate Compositional Color Descriptions

arXiv: https://arxiv.org/abs/1606.03821 · HTML: https://mlsanity.com/paper/1606.03821/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2016.

## Built on by (most cited first, 2 of 2)

- [Perceptual Structure in the Absence of Grounding for LLMs: The Impact of Abstractedness and Subjectivity in Color Language](https://mlsanity.com/paper/2311.13105/) (2023)
- [Generating Compositional Color Representations from Text](https://mlsanity.com/paper/2109.10477/) (2021)

## Abstract (arXiv)

The production of color language is essential for grounded language generation. Color descriptions have many challenging properties: they can be vague, compositionally complex, and denotationally rich. We present an effective approach to generating color descriptions using recurrent neural networks and a Fourier-transformed color representation. Our model outperforms previous work on a conditional language modeling task over a large corpus of naturalistic color descriptions. In addition, probing the model's output reveals that it can accurately produce not only basic color terms but also descriptors with non-convex denotations ("greenish"), bare modifiers ("bright", "dull"), and compositional phrases ("faded teal") not seen in training.