{"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/talk-the-walk-navigating-new-york-city","title":"Talk the Walk: Navigating New York City through Grounded Dialogue","arxiv_id":"1807.03367","date":"2018-07-09","proceeding":null,"authors":["Harm de Vries","Kurt Shuster","Dhruv Batra","Devi Parikh","Jason Weston","Douwe Kiela"],"abstract":"We introduce \"Talk The Walk\", the first large-scale dialogue dataset grounded\nin action and perception. The task involves two agents (a \"guide\" and a\n\"tourist\") that communicate via natural language in order to achieve a common\ngoal: having the tourist navigate to a given target location. The task and\ndataset, which are described in detail, are challenging and their full solution\nis an open problem that we pose to the community. We (i) focus on the task of\ntourist localization and develop the novel Masked Attention for Spatial\nConvolutions (MASC) mechanism that allows for grounding tourist utterances into\nthe guide's map, (ii) show it yields significant improvements for both emergent\nand natural language communication, and (iii) using this method, we establish\nnon-trivial baselines on the full task.","url_abs":"http://arxiv.org/abs/1807.03367v3","url_pdf":"http://arxiv.org/pdf/1807.03367v3.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":"talk-the-walk-navigating-new-york-city","repo_url":"https://github.com/facebookresearch/talkthewalk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[{"slug":"talk-the-walk","name":"Talk the Walk","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.03367","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}