{"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":"/dataset/sgd","name":"SGD","full_name":"Schema-Guided Dialogue","description_markdown":"The Schema-Guided Dialogue (SGD) dataset consists of over 20k annotated multi-domain, task-oriented conversations between a human and a virtual assistant. These conversations involve interactions with services and APIs spanning 20 domains, ranging from banks and events to media, calendar, travel, and weather. For most of these domains, the dataset contains multiple different APIs, many of which have overlapping functionalities but different interfaces, which reflects common real-world scenarios. The wide range of available annotations can be used for intent prediction, slot filling, dialogue state tracking, policy imitation learning, language generation, user simulation learning, among other tasks in large-scale virtual assistants. Besides these, the dataset has unseen domains and services in the evaluation set to quantify the performance in zero-shot or few shot settings.\r\n\r\nSource: [The Schema-Guided Dialogue Dataset](https://github.com/google-research-datasets/dstc8-schema-guided-dialogue)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/dstc8-schema-guided-dialogue","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/towards-scalable-multi-domain-conversational","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","first_author":"Abhinav Rastogi","url":null},"license":{"name":"CC-BY-SA-4.0","url":"https://github.com/google-research-datasets/dstc8-schema-guided-dialogue"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Dialogue State Tracking","url":"/task/dialogue-state-tracking","datasets_with_task":"/datasets/task/dialogue-state-tracking"},{"name":"Task-Oriented Dialogue Systems","url":"/task/task-oriented-dialogue-systems","datasets_with_task":"/datasets/task/task-oriented-dialogue-systems"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Multi-domain Dialogue State Tracking","url":"/task/multi-domain-dialogue-state-tracking","datasets_with_task":"/datasets/task/multi-domain-dialogue-state-tracking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SGD"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/schema_guided_dstc8","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/schema_guided_dstc8","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#googlesgd","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/schema_guided_dialogue","frameworks":["tf","jax"]},{"repo":"https://github.com/google-research-datasets/dstc8-schema-guided-dialogue","url":"https://github.com/google-research-datasets/dstc8-schema-guided-dialogue","frameworks":[]}],"num_papers_in_archive":186,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/task-oriented-dialogue-systems-on-sgd","task":"Task-Oriented Dialogue Systems","dataset_variant":"SGD","rows":2,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"T5","paper":"/paper/the-gem-benchmark-natural-language-generation","metrics":{"METEOR":"0.331"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/classification-on-sgd","task":"Classification","dataset_variant":"SGD","rows":1,"metrics":["F1 (Seqeval)"],"first_row_in_archive_order":{"model":"SGD_ss","paper":"/paper/a-sequence-to-sequence-approach-to-dialogue","metrics":{"F1 (Seqeval)":"2020"},"code_links":[{"title":"sweetalyssum/Seq2Seq-DU","url":"https://github.com/sweetalyssum/Seq2Seq-DU"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/the-gem-benchmark-natural-language-generation","slug":"the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","arxiv_id":"2102.01672","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-sequence-to-sequence-approach-to-dialogue","slug":"a-sequence-to-sequence-approach-to-dialogue","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","date":"2020-11-18","arxiv_id":"2011.09553","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/the-gem-benchmark-natural-language-generation","slug":"the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","arxiv_id":"2102.01672","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-sequence-to-sequence-approach-to-dialogue","slug":"a-sequence-to-sequence-approach-to-dialogue","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","date":"2020-11-18","arxiv_id":"2011.09553","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"db995be6a7c47d67186bf0cf6247b21466d3c227877bbe7788f1251a8ed60749","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}