{"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-speak-and-act-in-a-fantasy-text","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","arxiv_id":"1903.03094","date":"2019-03-07","proceeding":"IJCNLP 2019 11","authors":["Jack Urbanek","Angela Fan","Siddharth Karamcheti","Saachi Jain","Samuel Humeau","Emily Dinan","Tim Rocktäschel","Douwe Kiela","Arthur Szlam","Jason Weston"],"abstract":"We introduce a large scale crowdsourced text adventure game as a research\nplatform for studying grounded dialogue. In it, agents can perceive, emote, and\nact whilst conducting dialogue with other agents. Models and humans can both\nact as characters within the game. We describe the results of training\nstate-of-the-art generative and retrieval models in this setting. We show that\nin addition to using past dialogue, these models are able to effectively use\nthe state of the underlying world to condition their predictions. In\nparticular, we show that grounding on the details of the local environment,\nincluding location descriptions, and the objects (and their affordances) and\ncharacters (and their previous actions) present within it allows better\npredictions of agent behavior and dialogue. We analyze the ingredients\nnecessary for successful grounding in this setting, and how each of these\nfactors relate to agents that can talk and act successfully.","url_abs":"http://arxiv.org/abs/1903.03094v1","url_pdf":"http://arxiv.org/pdf/1903.03094v1.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-speak-and-act-in-a-fantasy-text","repo_url":"https://github.com/facebookresearch/light","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03094"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/facebookresearch/light","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":7,"samples":[{"code_sha256_prefix":"429b470316991a46","entry":"build_filler_rooms","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/filler_rooms.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/filler_rooms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"429b470316991a46"}},{"code_sha256_prefix":"f0295591ca0365e1","entry":"build_filler_rooms_from_categories","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/filler_rooms.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/filler_rooms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f0295591ca0365e1"}},{"code_sha256_prefix":"464bffb0c480285e","entry":"clear_bit","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/onboarding_flags.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/onboarding_flags.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"464bffb0c480285e"}},{"code_sha256_prefix":"fcb6ee5965ad9127","entry":"format_list_for_sql","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/light_database.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/light_database.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"fcb6ee5965ad9127"}},{"code_sha256_prefix":"a0d7172c8f73cca3","entry":"set_bit","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/onboarding_flags.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/onboarding_flags.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a0d7172c8f73cca3"}},{"code_sha256_prefix":"87e4293f1c69c29f","entry":"test_bit","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/onboarding_flags.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/onboarding_flags.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"87e4293f1c69c29f"}},{"code_sha256_prefix":"f7c7236401e74b16","entry":"to_legacy_dict","repo":"facebookresearch/light","repo_kind":"official","path":"light/data_model/filler_rooms.py","file_url":"https://github.com/facebookresearch/light/blob/HEAD/light/data_model/filler_rooms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f7c7236401e74b16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}