{"url":"/task/dialogue","name":"Dialogue","slug":"dialogue","description_markdown":"Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.","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":"derived"},"counts":{"papers_tagged":1,"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":0,"subtasks":21,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/dialogue-on-persona-chat","slug":"dialogue-on-persona-chat","dataset":"Persona-Chat","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU-1","BLEU-2","Distinct-1","Distinct-2"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper_title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","paper_url":"/paper/textbox-2-0-a-text-generation-library-with","paper_date":"2022-12-26","arxiv_id":"2212.13005","code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[],"subtasks":[{"url":"/task/conversation-disentanglement","name":"Conversation Disentanglement"},{"url":"/task/dialog-learning","name":"Dialog Learning"},{"url":"/task/dialogue-act-classification","name":"Dialogue Act Classification"},{"url":"/task/dialogue-generation","name":"Dialogue Generation"},{"url":"/task/dialogue-interpretation","name":"Dialogue Interpretation"},{"url":"/task/dialogue-management","name":"Dialogue Management"},{"url":"/task/dialogue-state-tracking","name":"Dialogue State Tracking"},{"url":"/task/dialogue-understanding","name":"Dialogue Understanding"},{"url":"/task/empathetic-response-generation","name":"Empathetic Response Generation"},{"url":"/task/end-to-end-dialogue-modelling","name":"End-To-End Dialogue Modelling"},{"url":"/task/goal-oriented-dialog","name":"Goal-Oriented Dialog"},{"url":"/task/goal-oriented-dialogue-systems","name":"Goal-Oriented Dialogue Systems"},{"url":"/task/interactive-evaluation-of-dialog","name":"Interactive Evaluation of Dialog"},{"url":"/task/multimodal-gif-dialog","name":"Multimodal GIF Dialog"},{"url":"/task/pesona-dialogue-in-story","name":"Persona Dialogue in Story"},{"url":"/task/problem-solving-deliberation","name":"Problem-Solving Deliberation"},{"url":"/task/short-text-conversation","name":"Short-Text Conversation"},{"url":"/task/task-completion-dialogue-policy-learning","name":"Task-Completion Dialogue Policy Learning"},{"url":"/task/task-oriented-dialogue-systems","name":"Task-Oriented Dialogue Systems"},{"url":"/task/visual-dialogue","name":"Visual Dialog"},{"url":"/task/workflow-discovery","name":"Workflow Discovery"}],"parent_tasks":[],"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":1,"items":[{"url":"/paper/textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","arxiv_id":"2212.13005","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":1,"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"}}