{"url":"/sota/task-oriented-dialogue-systems-on-kvret","task":{"name":"Task-Oriented Dialogue Systems","url":"/task/task-oriented-dialogue-systems","note":null},"dataset":{"name":"KVRET","url":null},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Achieving a pre-defined task through a dialog.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Entity F1","BLEU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Entity F1":"higher","BLEU":"higher"}},"counts":{"rows":10,"rows_with_code":8,"rows_with_paper_page":10,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"T5-3b(UnifiedSKG)","metrics":{"Entity F1":"70.07"},"uses_additional_data":false,"paper_date":"2022-01-16","paper":"/paper/unifiedskg-unifying-and-multi-tasking","paper_url":"https://arxiv.org/abs/2201.05966v3","paper_title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","code":"https://github.com/hkunlp/unifiedskg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"COMET","metrics":{"BLEU":"17.3","Entity F1":"63.6"},"uses_additional_data":false,"paper_date":"2020-10-12","paper":"/paper/dynamic-memory-enhanced-transformer-for-end","paper_url":"https://arxiv.org/abs/2010.05740v4","paper_title":"Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"DF-Net","metrics":{"BLEU":"15.2","Entity F1":"62.5"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/dynamic-fusion-network-for-multi-domain-end","paper_url":"https://arxiv.org/abs/2004.11019v3","paper_title":"Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog","code":"https://github.com/LooperXX/DF-Net","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"GLMP","metrics":{"BLEU":"14.79","Entity F1":"59.97"},"uses_additional_data":false,"paper_date":"2019-01-15","paper":"/paper/global-to-local-memory-pointer-networks-for","paper_url":"http://arxiv.org/abs/1901.04713v2","paper_title":"Global-to-local Memory Pointer Networks for Task-Oriented Dialogue","code":"https://github.com/jasonwu0731/GLMP","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"TTOS","metrics":{"BLEU":"17.35","Entity F1":"55.38"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/amalgamating-knowledge-from-two-teachers-for","paper_url":"https://aclanthology.org/2020.emnlp-main.281","paper_title":"Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training","code":"https://github.com/siat-nlp/TTOS","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"KB-retriever","metrics":{"BLEU":"13.9","Entity F1":"53.7"},"uses_additional_data":false,"paper_date":"2019-09-15","paper":"/paper/entity-consistent-end-to-end-task-oriented","paper_url":"https://arxiv.org/abs/1909.06762v2","paper_title":"Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever","code":"https://github.com/yizhen20133868/Retriever-Dialogue","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DSR","metrics":{"BLEU":"12.7","Entity F1":"51.9"},"uses_additional_data":false,"paper_date":"2018-06-12","paper":"/paper/sequence-to-sequence-learning-for-task","paper_url":"http://arxiv.org/abs/1806.04441v1","paper_title":"Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"KV Retrieval Net","metrics":{"BLEU":"13.2","Entity F1":"48.0"},"uses_additional_data":false,"paper_date":"2017-05-15","paper":"/paper/key-value-retrieval-networks-for-task","paper_url":"http://arxiv.org/abs/1705.05414v2","paper_title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","code":"https://github.com/ysglh/Task-Oriented-Dialogue-Dataset-Survey","n_code_links":3,"syntology":null},{"rank_in_archive_order":9,"model":"THPN","metrics":{"BLEU":"12.8","Entity F1":"37.8"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/a-template-guided-hybrid-pointer-network-for-1","paper_url":"https://aclanthology.org/2021.dialdoc-1.3","paper_title":"A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems","code":"https://github.com/wdimmy/THPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Mem2Seq","metrics":{"BLEU":"12.6","Entity F1":"33.4"},"uses_additional_data":false,"paper_date":"2018-04-23","paper":"/paper/mem2seq-effectively-incorporating-knowledge","paper_url":"http://arxiv.org/abs/1804.08217v3","paper_title":"Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems","code":"https://github.com/HLTCHKUST/Mem2Seq","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}