{"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/wizard-of-wikipedia-knowledge-powered","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","arxiv_id":"1811.01241","date":"2018-11-03","proceeding":"ICLR 2019 5","authors":["Emily Dinan","Stephen Roller","Kurt Shuster","Angela Fan","Michael Auli","Jason Weston"],"abstract":"In open-domain dialogue intelligent agents should exhibit the use of\nknowledge, however there are few convincing demonstrations of this to date. The\nmost popular sequence to sequence models typically \"generate and hope\" generic\nutterances that can be memorized in the weights of the model when mapping from\ninput utterance(s) to output, rather than employing recalled knowledge as\ncontext. Use of knowledge has so far proved difficult, in part because of the\nlack of a supervised learning benchmark task which exhibits knowledgeable open\ndialogue with clear grounding. To that end we collect and release a large\ndataset with conversations directly grounded with knowledge retrieved from\nWikipedia. We then design architectures capable of retrieving knowledge,\nreading and conditioning on it, and finally generating natural responses. Our\nbest performing dialogue models are able to conduct knowledgeable discussions\non open-domain topics as evaluated by automatic metrics and human evaluations,\nwhile our new benchmark allows for measuring further improvements in this\nimportant research direction.","url_abs":"http://arxiv.org/abs/1811.01241v2","url_pdf":"http://arxiv.org/pdf/1811.01241v2.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":"wizard-of-wikipedia-knowledge-powered","repo_url":"https://github.com/facebookresearch/ParlAI/tree/master/projects/wizard_of_wikipedia","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"wizard-of-wikipedia-knowledge-powered","repo_url":"https://github.com/informagi/conversational-entity-linking-2022","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"wizard-of-wikipedia-knowledge-powered","repo_url":"https://github.com/mangopy/direct-rag-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"}],"methods":[],"datasets_introduced":[{"slug":"wizard-of-wikipedia","name":"Wizard of Wikipedia","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.01241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01241"}},"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/ParlAI/tree/master/projects/wizard_of_wikipedia","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mangopy/direct-rag-learning","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/informagi/conversational-entity-linking-2022","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"e25e20b71abcc3f8","entry":"extract_mentions_to_predicted_clusters_from_clusters","repo":"informagi/conversational-entity-linking-2022","repo_kind":"listed","path":"tool/s2e_pe/utils.py","file_url":"https://github.com/informagi/conversational-entity-linking-2022/blob/HEAD/tool/s2e_pe/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e25e20b71abcc3f8"}},{"code_sha256_prefix":"9fc056a7d690a0ad","entry":"flatten_list_of_lists","repo":"informagi/conversational-entity-linking-2022","repo_kind":"listed","path":"tool/s2e_pe/utils.py","file_url":"https://github.com/informagi/conversational-entity-linking-2022/blob/HEAD/tool/s2e_pe/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fc056a7d690a0ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}