{"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/colors-in-context-a-pragmatic-neural-model","title":"Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding","arxiv_id":"1703.10186","date":"2017-03-29","proceeding":"TACL 2017 1","authors":["Will Monroe","Robert X. D. Hawkins","Noah D. Goodman","Christopher Potts"],"abstract":"We present a model of pragmatic referring expression interpretation in a\ngrounded communication task (identifying colors from descriptions) that draws\nupon predictions from two recurrent neural network classifiers, a speaker and a\nlistener, unified by a recursive pragmatic reasoning framework. Experiments\nshow that this combined pragmatic model interprets color descriptions more\naccurately than the classifiers from which it is built, and that much of this\nimprovement results from combining the speaker and listener perspectives. We\nobserve that pragmatic reasoning helps primarily in the hardest cases: when the\nmodel must distinguish very similar colors, or when few utterances adequately\nexpress the target color. Our findings make use of a newly-collected corpus of\nhuman utterances in color reference games, which exhibit a variety of pragmatic\nbehaviors. We also show that the embedded speaker model reproduces many of\nthese pragmatic behaviors.","url_abs":"http://arxiv.org/abs/1703.10186v2","url_pdf":"http://arxiv.org/pdf/1703.10186v2.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":"colors-in-context-a-pragmatic-neural-model","repo_url":"https://github.com/futurulus/colors-in-context","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"referring-expression","task_name":"Referring Expression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.10186","atlas_url":"https://app.syntology.ai/?focus=1703.10186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10186"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/futurulus/colors-in-context","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"6ade32a755999e8b","entry":"get_example_inst","repo":"futurulus/colors-in-context","repo_kind":"listed","path":"run_experiment.py","file_url":"https://github.com/futurulus/colors-in-context/blob/HEAD/run_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ade32a755999e8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}