{"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_with_a_benchmark_row":[{"paper":"/paper/the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-sequence-to-sequence-approach-to-dialogue","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","date":"2020-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}