{"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/generating-bilingual-pragmatic-color","title":"Generating Bilingual Pragmatic Color References","arxiv_id":"1803.03917","date":"2018-03-11","proceeding":"NAACL 2018 6","authors":["Will Monroe","Jennifer Hu","Andrew Jong","Christopher Potts"],"abstract":"Contextual influences on language often exhibit substantial cross-lingual\nregularities; for example, we are more verbose in situations that require finer\ndistinctions. However, these regularities are sometimes obscured by semantic\nand syntactic differences. Using a newly-collected dataset of color reference\ngames in Mandarin Chinese (which we release to the public), we confirm that a\nvariety of constructions display the same sensitivity to contextual difficulty\nin Chinese and English. We then show that a neural speaker agent trained on\nbilingual data with a simple multitask learning approach displays more\nhuman-like patterns of context dependence and is more pragmatically informative\nthan its monolingual Chinese counterpart. Moreover, this is not at the expense\nof language-specific semantic understanding: the resulting speaker model learns\nthe different basic color term systems of English and Chinese (with noteworthy\ncross-lingual influences), and it can identify synonyms between the two\nlanguages using vector analogy operations on its output layer, despite having\nno exposure to parallel data.","url_abs":"http://arxiv.org/abs/1803.03917v2","url_pdf":"http://arxiv.org/pdf/1803.03917v2.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":"generating-bilingual-pragmatic-color","repo_url":"https://github.com/futurulus/colors-in-context","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.03917","atlas_url":"https://app.syntology.ai/?focus=1803.03917","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}