{"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":"/task/end-to-end-dialogue-modelling","name":"End-To-End Dialogue Modelling","slug":"end-to-end-dialogue-modelling","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":11,"papers_with_code":8,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/end-to-end-dialogue-modelling-on-multiwoz-2-0","slug":"end-to-end-dialogue-modelling-on-multiwoz-2-0","dataset":"MULTIWOZ 2.0","dataset_url":"/dataset/multiwoz","rows_in_archive":6,"metrics":["MultiWOZ (Success)","MultiWOZ (Inform)","BLEU"],"first_row_in_archive_order":{"model":"GALAXY","paper_title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","paper_url":"/paper/galaxy-a-generative-pre-trained-model-for","paper_date":"2021-11-29","arxiv_id":"2111.14592","code_links":[{"title":"siat-nlp/galaxy","url":"https://github.com/siat-nlp/galaxy"}],"syntology":null}},{"leaderboard":"/sota/end-to-end-dialogue-modelling-on-multiwoz-2-1","slug":"end-to-end-dialogue-modelling-on-multiwoz-2-1","dataset":"MULTIWOZ 2.1","dataset_url":"/dataset/multiwoz","rows_in_archive":4,"metrics":["BLEU","MultiWOZ (Inform)","MultiWOZ (Success)"],"first_row_in_archive_order":{"model":"GALAXY","paper_title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","paper_url":"/paper/galaxy-a-generative-pre-trained-model-for","paper_date":"2021-11-29","arxiv_id":"2111.14592","code_links":[{"title":"siat-nlp/galaxy","url":"https://github.com/siat-nlp/galaxy"}],"syntology":null}}],"datasets":[{"url":"/dataset/multiwoz","name":"MultiWOZ","full_name":"Multi-domain Wizard-of-Oz","num_papers_in_archive":328},{"url":"/dataset/bitod","name":"BiToD","full_name":"","num_papers_in_archive":9},{"url":"/dataset/arabic-tod","name":"Arabic-ToD","full_name":"Arabic-ToD: Arabic Task Oriented Dialogue dataset","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/dialogue","name":"Dialogue"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":11,"of":11,"of_with_code":8,"tagged_in_all":11,"counts":{"archive_papers_tagged":11,"with_a_code_link":8,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/task-oriented-dialog-systems-that-consider","slug":"task-oriented-dialog-systems-that-consider","title":"Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context","date":"2019-11-24","arxiv_id":"1911.10484","repositories_listed":6,"syntology":null},{"url":"/paper/multi-task-pre-training-for-plug-and-play","slug":"multi-task-pre-training-for-plug-and-play","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","date":"2021-09-29","arxiv_id":"2109.14739","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-pre-training-for-plug-and-play#ran","syntology_url":"https://syntology.ai/paper/2109.14739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14739"}},"official":{"repos":["awslabs/pptod"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/galaxy-a-generative-pre-trained-model-for","slug":"galaxy-a-generative-pre-trained-model-for","title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","date":"2021-11-29","arxiv_id":"2111.14592","repositories_listed":1,"syntology":null},{"url":"/paper/maintaining-common-ground-in-dynamic","slug":"maintaining-common-ground-in-dynamic","title":"Maintaining Common Ground in Dynamic Environments","date":"2021-05-29","arxiv_id":"2105.14207","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/maintaining-common-ground-in-dynamic#ran","syntology_url":"https://syntology.ai/paper/2105.14207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14207"}},"official":{"repos":["Alab-NII/dynamic-onecommon"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/augpt-dialogue-with-pre-trained-language","slug":"augpt-dialogue-with-pre-trained-language","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","date":"2021-02-09","arxiv_id":"2102.05126","repositories_listed":1,"syntology":null},{"url":"/paper/a-probabilistic-end-to-end-task-oriented","slug":"a-probabilistic-end-to-end-task-oriented","title":"A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning","date":"2020-09-17","arxiv_id":"2009.08115","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/a-probabilistic-end-to-end-task-oriented#ran","syntology_url":"https://syntology.ai/paper/2009.08115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.08115"}},"official":{"repos":["thu-spmi/LABES"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/soloist-few-shot-task-oriented-dialog-with-a","slug":"soloist-few-shot-task-oriented-dialog-with-a","title":"SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching","date":"2020-05-11","arxiv_id":"2005.05298","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/soloist-few-shot-task-oriented-dialog-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.05298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05298"}},"official":null}},{"url":"/paper/a-simple-language-model-for-task-oriented","slug":"a-simple-language-model-for-task-oriented","title":"A Simple Language Model for Task-Oriented Dialogue","date":"2020-05-02","arxiv_id":"2005.00796","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-simple-language-model-for-task-oriented#ran","syntology_url":"https://syntology.ai/paper/2005.00796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00796"}},"official":{"repos":["salesforce/simpletod"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":null,"slug":"cross-lingual-dialogue-dataset-creation-via","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","date":"2022-01-31","arxiv_id":"2201.13405","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-pre-training-for-plug-and-play-1","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/pretraining-the-noisy-channel-model-for-task","slug":"pretraining-the-noisy-channel-model-for-task","title":"Pretraining the Noisy Channel Model for Task-Oriented Dialogue","date":"2021-03-18","arxiv_id":"2103.10518","repositories_listed":0,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/end-to-end-dialogue-modelling/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/end-to-end-dialogue-modelling/papers/ran/1","json":"/task/end-to-end-dialogue-modelling/papers/ran/1.json","rows":4}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"56154c3d0c1e59b47bbc9665e6ec11f07cb7fa5b1cb5335af9bff5e2f15b21fe","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}