{"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/emergent-communication-in-a-multi-modal-multi","title":"Emergent Communication in a Multi-Modal, Multi-Step Referential Game","arxiv_id":"1705.10369","date":"2017-05-29","proceeding":"ICLR 2018 1","authors":["Katrina Evtimova","Andrew Drozdov","Douwe Kiela","Kyunghyun Cho"],"abstract":"Inspired by previous work on emergent communication in referential games, we\npropose a novel multi-modal, multi-step referential game, where the sender and\nreceiver have access to distinct modalities of an object, and their information\nexchange is bidirectional and of arbitrary duration. The multi-modal multi-step\nsetting allows agents to develop an internal communication significantly closer\nto natural language, in that they share a single set of messages, and that the\nlength of the conversation may vary according to the difficulty of the task. We\nexamine these properties empirically using a dataset consisting of images and\ntextual descriptions of mammals, where the agents are tasked with identifying\nthe correct object. Our experiments indicate that a robust and efficient\ncommunication protocol emerges, where gradual information exchange informs\nbetter predictions and higher communication bandwidth improves generalization.","url_abs":"http://arxiv.org/abs/1705.10369v4","url_pdf":"http://arxiv.org/pdf/1705.10369v4.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":"emergent-communication-in-a-multi-modal-multi","repo_url":"https://github.com/nyu-dl/MultimodalGame","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1705.10369","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}