{"url":"/task/workflow-discovery","name":"Workflow Discovery","slug":"workflow-discovery","description_markdown":"Workflow Discovery (WD) was introduced by [Workflow Discovery from Dialogues in the Low Data Regime](https://openreview.net/forum?id=L9othQvPks). WD aims to extract work-flows that have either implicitly or explicitly guided task-oriented dialogues be-\r\ntween two people. Workflows extracted from a conversation consist of a summary of the key actions taken during\r\nthe dialogue. These workflows consist of pre-defined terms for actions and slots when possible, but our approach also al-\r\nlows for actions that are not known to be invented by the model online and used as new steps in the generated work-\r\nflow.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2,"papers_with_code":1,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/workflow-discovery-on-abcd","slug":"workflow-discovery-on-abcd","dataset":"ABCD","dataset_url":"/dataset/abcd","rows_in_archive":1,"metrics":["In-domain EM","In-domain CE","Cross-domain EM","Cross-domain  CE"],"first_row_in_archive_order":{"model":"T5-Large","paper_title":"Workflow Discovery from Dialogues in the Low Data Regime","paper_url":"/paper/workflow-discovery-from-dialogues-in-the-low","paper_date":"2022-05-24","arxiv_id":"2205.11690","code_links":[{"title":"ServiceNow/research-workflow-discovery","url":"https://github.com/ServiceNow/research-workflow-discovery"}],"syntology":null}}],"datasets":[{"url":"/dataset/abcd","name":"ABCD","full_name":"Action-Based Conversations Dataset","num_papers_in_archive":10}],"subtasks":[],"parent_tasks":[{"url":"/task/dialogue","name":"Dialogue"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":1,"of":1,"tagged_in_all":2,"items":[{"url":"/paper/workflow-discovery-from-dialogues-in-the-low","title":"Workflow Discovery from Dialogues in the Low Data Regime","date":"2022-05-24","arxiv_id":"2205.11690","repositories_listed":1,"syntology":null}],"syntology_records":0,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}