Learning to Generate Compositional Color Descriptions
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2016
- DOI:
- 10.48550/arXiv.1606.03821
- arXiv:
- arXiv:1606.03821
- Bibcode:
- 2016arXiv160603821M
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- 6 pages, 4 figures, 3 tables. EMNLP 2016