{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/openvidial-2-0-a-larger-scale-open-domain","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","arxiv_id":"2109.12761","date":"2021-09-27","proceeding":null,"authors":["Shuhe Wang","Yuxian Meng","Xiaoya Li","Xiaofei Sun","Rongbin Ouyang","Jiwei Li"],"abstract":"In order to better simulate the real human conversation process, models need to generate dialogue utterances based on not only preceding textual contexts but also visual contexts. However, with the development of multi-modal dialogue learning, the dataset scale gradually becomes a bottleneck. In this report, we release OpenViDial 2.0, a larger-scale open-domain multi-modal dialogue dataset compared to the previous version OpenViDial 1.0. OpenViDial 2.0 contains a total number of 5.6 million dialogue turns extracted from either movies or TV series from different resources, and each dialogue turn is paired with its corresponding visual context. We hope this large-scale dataset can help facilitate future researches on open-domain multi-modal dialog generation, e.g., multi-modal pretraining for dialogue generation.","url_abs":"https://arxiv.org/abs/2109.12761v2","url_pdf":"https://arxiv.org/pdf/2109.12761v2.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":"openvidial-2-0-a-larger-scale-open-domain","repo_url":"https://github.com/ShannonAI/OpenViDial","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"multi-modal-dialogue-generation","task_name":"Multi-modal Dialogue Generation"}],"methods":[],"datasets_introduced":[{"slug":"openvidial-2-0","name":"OpenViDial 2.0","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-modal-dialogue-generation-on-openvidial","task":"Multi-modal Dialogue Generation","dataset":"OpenViDial 2.0","model":"FV (w/o MI)","rank_in_archive_order":1,"of":4,"metrics":{"BLEU":"1.99","Dis-1":"0.0056","Dis-2":"0.0431","Dis-3":"0.125","Dis-4":"0.2215"},"uses_additional_data":false},{"leaderboard":"/sota/multi-modal-dialogue-generation-on-openvidial","task":"Multi-modal Dialogue Generation","dataset":"OpenViDial 2.0","model":"CV (w/o MI)","rank_in_archive_order":2,"of":4,"metrics":{"BLEU":"1.97","Dis-1":"0.0041","Dis-2":"0.0353","Dis-3":"0.0999","Dis-4":"0.1726"},"uses_additional_data":false},{"leaderboard":"/sota/multi-modal-dialogue-generation-on-openvidial","task":"Multi-modal Dialogue Generation","dataset":"OpenViDial 2.0","model":"NV (w/ MI)","rank_in_archive_order":3,"of":4,"metrics":{"BLEU":"1.96","Dis-1":"0.0039","Dis-2":"0.0311","Dis-3":"0.0953","Dis-4":"0.163"},"uses_additional_data":false},{"leaderboard":"/sota/multi-modal-dialogue-generation-on-openvidial","task":"Multi-modal Dialogue Generation","dataset":"OpenViDial 2.0","model":"NV (w/o MI)","rank_in_archive_order":4,"of":4,"metrics":{"BLEU":"1.95","Dis-1":"0.0037","Dis-2":"0.0302","Dis-3":"0.0929","Dis-4":"0.1711"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.12761","atlas_url":"https://app.syntology.ai/?focus=2109.12761","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2109.12761"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.12761\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.12761"},"call":"get_concepts_for_paper(arxiv_id=\"2109.12761\")"}],"by_repo":[{"repo":"ShannonAI/OpenViDial","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a11c1c708f4de3fc3d4032b5878625cf6e9622c0d055fc5284a2d50234514b43","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}