{"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/a-dataset-for-document-grounded-conversations","title":"A Dataset for Document Grounded Conversations","arxiv_id":"1809.07358","date":"2018-09-19","proceeding":"EMNLP 2018 10","authors":["Kangyan Zhou","Shrimai Prabhumoye","Alan W. black"],"abstract":"This paper introduces a document grounded dataset for text conversations. We\ndefine \"Document Grounded Conversations\" as conversations that are about the\ncontents of a specified document. In this dataset the specified documents were\nWikipedia articles about popular movies. The dataset contains 4112\nconversations with an average of 21.43 turns per conversation. This positions\nthis dataset to not only provide a relevant chat history while generating\nresponses but also provide a source of information that the models could use.\nWe describe two neural architectures that provide benchmark performance on the\ntask of generating the next response. We also evaluate our models for\nengagement and fluency, and find that the information from the document helps\nin generating more engaging and fluent responses.","url_abs":"http://arxiv.org/abs/1809.07358v1","url_pdf":"http://arxiv.org/pdf/1809.07358v1.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":"a-dataset-for-document-grounded-conversations","repo_url":"https://github.com/festvox/datasets-CMU_DoG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-dataset-for-document-grounded-conversations","repo_url":"https://github.com/AnblueWang/PGser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-dataset-for-document-grounded-conversations","repo_url":"https://github.com/lizekang/ITDD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"}],"methods":[],"datasets_introduced":[{"slug":"cmu-dog","name":"CMU DoG","full_name":"CMU Document Grounded Conversations Dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.07358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07358"}},"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/lizekang/ITDD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/festvox/datasets-CMU_DoG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AnblueWang/PGser","reach":{"status":"ok"}}],"summary":{"ran_honours":1},"by_repo_kind":{},"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":"0c8cfd6442c243f1","entry":"count_features","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0c8cfd6442c243f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}