{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-generate-compositional-color","title":"Learning to Generate Compositional Color Descriptions","arxiv_id":"1606.03821","date":"2016-06-13","proceeding":"EMNLP 2016 11","authors":["Will Monroe","Noah D. Goodman","Christopher Potts"],"abstract":"The production of color language is essential for grounded language\ngeneration. Color descriptions have many challenging properties: they can be\nvague, compositionally complex, and denotationally rich. We present an\neffective approach to generating color descriptions using recurrent neural\nnetworks and a Fourier-transformed color representation. Our model outperforms\nprevious work on a conditional language modeling task over a large corpus of\nnaturalistic color descriptions. In addition, probing the model's output\nreveals that it can accurately produce not only basic color terms but also\ndescriptors with non-convex denotations (\"greenish\"), bare modifiers (\"bright\",\n\"dull\"), and compositional phrases (\"faded teal\") not seen in training.","url_abs":"http://arxiv.org/abs/1606.03821v2","url_pdf":"http://arxiv.org/pdf/1606.03821v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-to-generate-compositional-color","repo_url":"https://github.com/stanfordnlp/color-describer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}