{"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/fusing-task-oriented-and-open-domain","title":"Fusing task-oriented and open-domain dialogues in conversational agents","arxiv_id":"2109.04137","date":"2021-09-09","proceeding":null,"authors":["Tom Young","Frank Xing","Vlad Pandelea","Jinjie Ni","Erik Cambria"],"abstract":"The goal of building intelligent dialogue systems has largely been separately pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform goal-oriented functions, and open-domain dialogue (ODD) systems, which focus on non-goal-oriented chitchat. The two dialogue modes can potentially be intertwined together seamlessly in the same conversation, as easily done by a friendly human assistant. Such ability is desirable in conversational agents, as the integration makes them more accessible and useful. Our paper addresses this problem of fusing TODs and ODDs in multi-turn dialogues. Based on the popular TOD dataset MultiWOZ, we build a new dataset FusedChat, by rewriting the existing TOD turns and adding new ODD turns. This procedure constructs conversation sessions containing exchanges from both dialogue modes. It features inter-mode contextual dependency, i.e., the dialogue turns from the two modes depend on each other. Rich dependency patterns including co-reference and ellipsis are features. The new dataset, with 60k new human-written ODD turns and 5k re-written TOD turns, offers a benchmark to test a dialogue model's ability to perform inter-mode conversations. This is a more challenging task since the model has to determine the appropriate dialogue mode and generate the response based on the inter-mode context. But such models would better mimic human-level conversation capabilities. We evaluate baseline models on this task, including classification-based two-stage models and two-in-one fused models. We publicly release FusedChat and the baselines to propel future work on inter-mode dialogue systems https://github.com/tomyoung903/FusedChat.","url_abs":"https://arxiv.org/abs/2109.04137v3","url_pdf":"https://arxiv.org/pdf/2109.04137v3.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":"fusing-task-oriented-and-open-domain","repo_url":"https://github.com/tomyoung903/fusedchat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"}],"methods":[],"datasets_introduced":[{"slug":"fusedchat","name":"FusedChat","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-generation-on-fusedchat","task":"Dialogue Generation","dataset":"FusedChat","model":"Classification-based model","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"12.17","Inform":"75.1","Inform_mct":"90.8","Joint SA":"0.600","PPL":"10.50","SSA":"0.55","Sensibleness":"0.58","Slot Accuracy":"0.973","Specificity":"0.51","Success":"60.9","Success_mct":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-generation-on-fusedchat","task":"Dialogue Generation","dataset":"FusedChat","model":"Two-in-one model","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"12.05","Inform":"70.4","Inform_mct":"90.1","Joint SA":"0.592","PPL":"10.49","SSA":"0.50","Sensibleness":"0.52","Slot Accuracy":"0.972","Specificity":"0.47","Success":"57.0","Success_mct":"72.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.04137","atlas_url":"https://app.syntology.ai/?focus=2109.04137","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":"2109.04137"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.04137\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.04137"},"call":"get_concepts_for_paper(arxiv_id=\"2109.04137\")"}],"by_repo":[{"repo":"tomyoung903/fusedchat","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["aaai_21416"],"harvested_for_calls":[]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"4592a9332c37a68d0a09030f99cce01360cc4a9249c1f752a94d9c8069c636ec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}