{"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":"/task/task-oriented-dialogue-systems","name":"Task-Oriented Dialogue Systems","slug":"task-oriented-dialogue-systems","description_markdown":"Achieving a pre-defined task through a dialog.","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":308,"papers_with_code":131,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":22,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/task-oriented-dialogue-systems-on-kvret","slug":"task-oriented-dialogue-systems-on-kvret","dataset":"KVRET","dataset_url":null,"rows_in_archive":10,"metrics":["Entity F1","BLEU"],"first_row_in_archive_order":{"model":"T5-3b(UnifiedSKG)","paper_title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","paper_url":"/paper/unifiedskg-unifying-and-multi-tasking","paper_date":"2022-01-16","arxiv_id":"2201.05966","code_links":[{"title":"hkunlp/unifiedskg","url":"https://github.com/hkunlp/unifiedskg"}],"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifiedskg-unifying-and-multi-tasking#ran","syntology_url":"https://syntology.ai/paper/2201.05966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05966"}},"official":{"repos":["hkunlp/unifiedskg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/task-oriented-dialogue-systems-on-sgd","slug":"task-oriented-dialogue-systems-on-sgd","dataset":"SGD","dataset_url":"/dataset/sgd","rows_in_archive":2,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"T5","paper_title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","paper_url":"/paper/the-gem-benchmark-natural-language-generation","paper_date":"2021-02-02","arxiv_id":"2102.01672","code_links":[],"syntology":null}},{"leaderboard":"/sota/task-oriented-dialogue-systems-on-kvret-1","slug":"task-oriented-dialogue-systems-on-kvret-1","dataset":"Kvret","dataset_url":null,"rows_in_archive":1,"metrics":["Entity F1"],"first_row_in_archive_order":{"model":"DF-Net","paper_title":"Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog","paper_url":"/paper/dynamic-fusion-network-for-multi-domain-end","paper_date":"2020-04-23","arxiv_id":"2004.11019","code_links":[{"title":"LooperXX/DF-Net","url":"https://github.com/LooperXX/DF-Net"}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/dynamic-fusion-network-for-multi-domain-end#ran","syntology_url":"https://syntology.ai/paper/2004.11019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11019"}},"official":{"repos":["LooperXX/DF-Net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/task-oriented-dialogue-systems-on-multiwoz-2","slug":"task-oriented-dialogue-systems-on-multiwoz-2","dataset":"MULTIWOZ 2.0","dataset_url":"/dataset/multiwoz","rows_in_archive":1,"metrics":["BLEU-4","Score"],"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_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}},"official":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/multiwoz","name":"MultiWOZ","full_name":"Multi-domain Wizard-of-Oz","num_papers_in_archive":328},{"url":"/dataset/sgd","name":"SGD","full_name":"Schema-Guided Dialogue","num_papers_in_archive":186},{"url":"/dataset/mutual","name":"MuTual","full_name":"MuTual","num_papers_in_archive":55},{"url":"/dataset/crosswoz","name":"CrossWOZ","full_name":"CrossWOZ","num_papers_in_archive":25},{"url":"/dataset/topv2","name":"TOPv2","full_name":"Task Oriented Parsing v2","num_papers_in_archive":25},{"url":"/dataset/abcd","name":"ABCD","full_name":"Action-Based Conversations Dataset","num_papers_in_archive":10},{"url":"/dataset/bitod","name":"BiToD","full_name":"","num_papers_in_archive":9},{"url":"/dataset/a-game-of-sorts","name":"A Game Of Sorts","full_name":"","num_papers_in_archive":4},{"url":"/dataset/odsqa","name":"ODSQA","full_name":"Open-Domain Spoken Question Answering","num_papers_in_archive":3},{"url":"/dataset/task2dial","name":"Task2Dial","full_name":"","num_papers_in_archive":3},{"url":"/dataset/ssd-1","name":"SSD","full_name":"Sub-Slot Dialogue dataset","num_papers_in_archive":2},{"url":"/dataset/ssd-phone","name":"SSD_PHONE","full_name":"Sub-Slot Dialogue dataset phone domain","num_papers_in_archive":2},{"url":"/dataset/arabic-tod","name":"Arabic-ToD","full_name":"Arabic-ToD: Arabic Task Oriented Dialogue dataset","num_papers_in_archive":1},{"url":"/dataset/benyfits","name":"BeNYfits","full_name":"New York City Public Benefits Eligibility Dialog Agent Benchmark","num_papers_in_archive":1},{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","num_papers_in_archive":1},{"url":"/dataset/hr-multiwoz","name":"HR-Multiwoz","full_name":"","num_papers_in_archive":1},{"url":"/dataset/incremental-dialog-dataset","name":"Incremental Dialog Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1},{"url":"/dataset/multiwoz-coref","name":"MultiWOZ-coref","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/ssd-id","name":"SSD_ID","full_name":"Sub-Slot Dialogue dataset id number domain","num_papers_in_archive":1},{"url":"/dataset/ssd-name","name":"SSD_NAME","full_name":"Sub-Slot Dialogue dataset name domain","num_papers_in_archive":1},{"url":"/dataset/ssd-plate","name":"SSD_PLATE","full_name":"Sub-Slot Dialogue dataset license plate number domain","num_papers_in_archive":1}],"subtasks":[{"url":"/task/sstod","name":"SSTOD"}],"parent_tasks":[{"url":"/task/dialogue","name":"Dialogue"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":308,"of_with_code":131,"tagged_in_all":308,"counts":{"archive_papers_tagged":308,"with_a_code_link":131,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":308,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":1,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/a-user-simulator-for-task-completion","slug":"a-user-simulator-for-task-completion","title":"A User Simulator for Task-Completion Dialogues","date":"2016-12-17","arxiv_id":"1612.05688","repositories_listed":10,"syntology":null},{"url":"/paper/global-to-local-memory-pointer-networks-for","slug":"global-to-local-memory-pointer-networks-for","title":"Global-to-local Memory Pointer Networks for Task-Oriented Dialogue","date":"2019-01-15","arxiv_id":"1901.04713","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/global-to-local-memory-pointer-networks-for#ran","syntology_url":"https://syntology.ai/paper/1901.04713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.04713"}},"official":{"repos":["jasonwu0731/GLMP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multiwoz-2-3-a-multi-domain-task-oriented","slug":"multiwoz-2-3-a-multi-domain-task-oriented","title":"MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation","date":"2020-10-12","arxiv_id":"2010.05594","repositories_listed":3,"syntology":null},{"url":"/paper/key-value-retrieval-networks-for-task","slug":"key-value-retrieval-networks-for-task","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","date":"2017-05-15","arxiv_id":"1705.05414","repositories_listed":3,"syntology":null},{"url":"/paper/dialight-lightweight-multilingual-development","slug":"dialight-lightweight-multilingual-development","title":"DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models","date":"2024-01-04","arxiv_id":"2401.02208","repositories_listed":2,"syntology":null},{"url":"/paper/in-context-learning-user-simulators-for-task","slug":"in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","date":"2023-06-01","arxiv_id":"2306.00774","repositories_listed":2,"syntology":null},{"url":"/paper/fantastic-rewards-and-how-to-tame-them-a-case","slug":"fantastic-rewards-and-how-to-tame-them-a-case","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","date":"2023-02-20","arxiv_id":"2302.10342","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fantastic-rewards-and-how-to-tame-them-a-case#ran","syntology_url":"https://syntology.ai/paper/2302.10342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10342"}},"official":{"repos":["budzianowski/multiwoz","shentao-yang/fantastic_reward_iclr2023"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/metaphorical-user-simulators-for-evaluating","slug":"metaphorical-user-simulators-for-evaluating","title":"Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems","date":"2022-04-02","arxiv_id":"2204.00763","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/metaphorical-user-simulators-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2204.00763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00763"}},"official":{"repos":["superbooming/simtester","sunnweiwei/metasim"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dora-toward-policy-optimization-for-task","slug":"dora-toward-policy-optimization-for-task","title":"DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context","date":"2021-07-07","arxiv_id":"2107.03286","repositories_listed":2,"syntology":null},{"url":"/paper/action-based-conversations-dataset-a-corpus","slug":"action-based-conversations-dataset-a-corpus","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","date":"2021-04-01","arxiv_id":"2104.00783","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/action-based-conversations-dataset-a-corpus#ran","syntology_url":"https://syntology.ai/paper/2104.00783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00783"}},"official":{"repos":["asappresearch/abcd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/conversation-graph-data-augmentation-training","slug":"conversation-graph-data-augmentation-training","title":"Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management","date":"2020-10-29","arxiv_id":"2010.15411","repositories_listed":2,"syntology":null},{"url":"/paper/modelling-hierarchical-structure-between","slug":"modelling-hierarchical-structure-between","title":"Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System","date":"2020-06-11","arxiv_id":"2006.06814","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-domain-apis-task-oriented","slug":"beyond-domain-apis-task-oriented","title":"Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access","date":"2020-06-05","arxiv_id":"2006.03533","repositories_listed":2,"syntology":null},{"url":"/paper/crosswoz-a-large-scale-chinese-cross-domain","slug":"crosswoz-a-large-scale-chinese-cross-domain","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","date":"2020-02-27","arxiv_id":"2002.11893","repositories_listed":2,"syntology":null},{"url":"/paper/retrospective-and-prospective-mixture-of","slug":"retrospective-and-prospective-mixture-of","title":"Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation","date":"2019-11-19","arxiv_id":"1911.08151","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrospective-and-prospective-mixture-of#ran","syntology_url":"https://syntology.ai/paper/1911.08151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08151"}},"official":{"repos":["budzianowski/multiwoz","Jiahuan-Pei/multiwoz-mdrg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/transferable-multi-domain-state-generator-for","slug":"transferable-multi-domain-state-generator-for","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","date":"2019-05-21","arxiv_id":"1905.08743","repositories_listed":2,"syntology":null},{"url":"/paper/global-locally-self-attentive-dialogue-state","slug":"global-locally-self-attentive-dialogue-state","title":"Global-Locally Self-Attentive Dialogue State Tracker","date":"2018-05-19","arxiv_id":"1805.09655","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/global-locally-self-attentive-dialogue-state#ran","syntology_url":"https://syntology.ai/paper/1805.09655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09655"}},"official":{"repos":["salesforce/glad"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/when-to-act-when-to-wait-modeling-structural","slug":"when-to-act-when-to-wait-modeling-structural","title":"WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue","date":"2025-06-02","arxiv_id":"2506.01881","repositories_listed":1,"syntology":null},{"url":"/paper/enstom-enhancing-dialogue-systems-with","slug":"enstom-enhancing-dialogue-systems-with","title":"EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance","date":"2025-05-22","arxiv_id":"2505.16526","repositories_listed":1,"syntology":null},{"url":"/paper/lanid-llm-assisted-new-intent-discovery","slug":"lanid-llm-assisted-new-intent-discovery","title":"LANID: LLM-assisted New Intent Discovery","date":"2025-03-31","arxiv_id":"2503.23740","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-graph-structures-and-large","slug":"leveraging-graph-structures-and-large","title":"Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues","date":"2025-01-21","arxiv_id":"2501.11977","repositories_listed":1,"syntology":null},{"url":"/paper/pseudo-label-enhanced-prototypical","slug":"pseudo-label-enhanced-prototypical","title":"Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery","date":"2024-10-26","arxiv_id":"2410.20219","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-estimation-for-llm-based-dialogue","slug":"confidence-estimation-for-llm-based-dialogue","title":"Confidence Estimation for LLM-Based Dialogue State Tracking","date":"2024-09-15","arxiv_id":"2409.09629","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/confidence-estimation-for-llm-based-dialogue#ran","syntology_url":"https://syntology.ai/paper/2409.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.09629"}},"official":{"repos":["jennycs0830/confidence_score_dst"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-mutual-learning-of-dialogue","slug":"unsupervised-mutual-learning-of-dialogue","title":"Unsupervised Mutual Learning of Dialogue Discourse Parsing and Topic Segmentation","date":"2024-05-30","arxiv_id":"2405.19799","repositories_listed":1,"syntology":null},{"url":"/paper/duetsim-building-user-simulator-with-dual","slug":"duetsim-building-user-simulator-with-dual","title":"DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues","date":"2024-05-16","arxiv_id":"2405.13028","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/duetsim-building-user-simulator-with-dual#ran","syntology_url":"https://syntology.ai/paper/2405.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13028"}},"official":{"repos":["suntea233/duetsim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/simulating-task-oriented-dialogues-with-state","slug":"simulating-task-oriented-dialogues-with-state","title":"Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models","date":"2024-04-23","arxiv_id":"2404.14772","repositories_listed":1,"syntology":null},{"url":"/paper/the-power-of-the-noisy-channel-unsupervised","slug":"the-power-of-the-noisy-channel-unsupervised","title":"Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel","date":"2024-04-23","arxiv_id":"2404.15219","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-evaluation-of-dialogue-systems","slug":"rethinking-the-evaluation-of-dialogue-systems","title":"Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs","date":"2024-04-19","arxiv_id":"2404.12994","repositories_listed":1,"syntology":null},{"url":"/paper/context-does-matter-implications-for","slug":"context-does-matter-implications-for","title":"Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems","date":"2024-04-15","arxiv_id":"2404.09980","repositories_listed":1,"syntology":null},{"url":"/paper/jmultiwoz-a-large-scale-japanese-multi-domain","slug":"jmultiwoz-a-large-scale-japanese-multi-domain","title":"JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset","date":"2024-03-26","arxiv_id":"2403.17319","repositories_listed":1,"syntology":null},{"url":"/paper/task-oriented-dialogue-with-in-context","slug":"task-oriented-dialogue-with-in-context","title":"Task-Oriented Dialogue with In-Context Learning","date":"2024-02-19","arxiv_id":"2402.12234","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-robustness-of-task-oriented","slug":"exploring-the-robustness-of-task-oriented","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","date":"2024-02-03","arxiv_id":"2402.02078","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-viability-of-synthetic-audio","slug":"exploring-the-viability-of-synthetic-audio","title":"Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking","date":"2023-12-04","arxiv_id":"2312.01842","repositories_listed":1,"syntology":null},{"url":"/paper/leeets-dial-linguistic-entrainment-in-end-to","slug":"leeets-dial-linguistic-entrainment-in-end-to","title":"LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems","date":"2023-11-15","arxiv_id":"2311.09390","repositories_listed":1,"syntology":null},{"url":"/paper/indotod-a-multi-domain-indonesian-benchmark","slug":"indotod-a-multi-domain-indonesian-benchmark","title":"IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems","date":"2023-11-02","arxiv_id":"2311.00958","repositories_listed":1,"syntology":null},{"url":"/paper/towards-llm-driven-dialogue-state-tracking","slug":"towards-llm-driven-dialogue-state-tracking","title":"Towards LLM-driven Dialogue State Tracking","date":"2023-10-23","arxiv_id":"2310.14970","repositories_listed":1,"syntology":null},{"url":"/paper/turn-level-active-learning-for-dialogue-state","slug":"turn-level-active-learning-for-dialogue-state","title":"Turn-Level Active Learning for Dialogue State Tracking","date":"2023-10-23","arxiv_id":"2310.14513","repositories_listed":1,"syntology":null},{"url":"/paper/instructtods-large-language-models-for-end-to","slug":"instructtods-large-language-models-for-end-to","title":"InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems","date":"2023-10-13","arxiv_id":"2310.08885","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-generation-alignment-for-end-to-end","slug":"retrieval-generation-alignment-for-end-to-end","title":"Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System","date":"2023-10-13","arxiv_id":"2310.08877","repositories_listed":1,"syntology":null},{"url":"/paper/improving-dialogue-management-quality","slug":"improving-dialogue-management-quality","title":"Improving Dialogue Management: Quality Datasets vs Models","date":"2023-10-02","arxiv_id":"2310.01339","repositories_listed":1,"syntology":null},{"url":"/paper/roll-up-your-sleeves-working-with-a","slug":"roll-up-your-sleeves-working-with-a","title":"Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System","date":"2023-07-29","arxiv_id":"2307.16081","repositories_listed":1,"syntology":null},{"url":"/paper/schema-guided-user-satisfaction-modeling-for","slug":"schema-guided-user-satisfaction-modeling-for","title":"Schema-Guided User Satisfaction Modeling for Task-Oriented Dialogues","date":"2023-05-26","arxiv_id":"2305.16798","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-intent-aware-encoders-for-zero","slug":"pre-training-intent-aware-encoders-for-zero","title":"Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification","date":"2023-05-24","arxiv_id":"2305.14827","repositories_listed":1,"syntology":null},{"url":"/paper/towards-asking-clarification-questions-for","slug":"towards-asking-clarification-questions-for","title":"Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues","date":"2023-05-23","arxiv_id":"2305.13690","repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-architecture-for-out-of-domain","slug":"a-hybrid-architecture-for-out-of-domain","title":"A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery","date":"2023-03-07","arxiv_id":"2303.04134","repositories_listed":1,"syntology":null},{"url":"/paper/textbox-2-0-a-text-generation-library-with","slug":"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_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}},"official":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/injecting-domain-knowledge-in-language-models","slug":"injecting-domain-knowledge-in-language-models","title":"Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems","date":"2022-12-15","arxiv_id":"2212.08120","repositories_listed":1,"syntology":null},{"url":"/paper/topic-aware-response-generation-in-task-1","slug":"topic-aware-response-generation-in-task-1","title":"Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access","date":"2022-12-10","arxiv_id":"2212.05373","repositories_listed":1,"syntology":null},{"url":"/paper/reranking-overgenerated-responses-for-end-to","slug":"reranking-overgenerated-responses-for-end-to","title":"Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems","date":"2022-11-07","arxiv_id":"2211.03648","repositories_listed":1,"syntology":null},{"url":"/paper/shift-reduce-task-oriented-semantic-parsing","slug":"shift-reduce-task-oriented-semantic-parsing","title":"Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers","date":"2022-10-21","arxiv_id":"2210.11984","repositories_listed":1,"syntology":null},{"url":"/paper/uninl-aligning-representation-learning-with","slug":"uninl-aligning-representation-learning-with","title":"UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning","date":"2022-10-19","arxiv_id":"2210.10722","repositories_listed":1,"syntology":null},{"url":"/paper/watch-the-neighbors-a-unified-k-nearest","slug":"watch-the-neighbors-a-unified-k-nearest","title":"Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery","date":"2022-10-17","arxiv_id":"2210.08909","repositories_listed":1,"syntology":null},{"url":"/paper/q-tod-a-query-driven-task-oriented-dialogue","slug":"q-tod-a-query-driven-task-oriented-dialogue","title":"Q-TOD: A Query-driven Task-oriented Dialogue System","date":"2022-10-14","arxiv_id":"2210.07564","repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-at-few-shot-out-of-distribution","slug":"a-closer-look-at-few-shot-out-of-distribution","title":"A Closer Look at Few-Shot Out-of-Distribution Intent Detection","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attention-modulation-for-zero-shot-cross","slug":"attention-modulation-for-zero-shot-cross","title":"Attention Modulation for Zero-Shot Cross-Domain Dialogue State Tracking","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/external-knowledge-selection-with-weighted","slug":"external-knowledge-selection-with-weighted","title":"External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems","date":"2022-09-06","arxiv_id":"2209.02251","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-task-oriented-dialogue-systems-with","slug":"efficient-task-oriented-dialogue-systems-with","title":"Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task","date":"2022-08-15","arxiv_id":"2208.07097","repositories_listed":1,"syntology":null},{"url":"/paper/act-aware-slot-value-predicting-in-multi","slug":"act-aware-slot-value-predicting-in-multi","title":"Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking","date":"2022-08-04","arxiv_id":"2208.02462","repositories_listed":1,"syntology":null},{"url":"/paper/post-processing-networks-method-for","slug":"post-processing-networks-method-for","title":"Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning","date":"2022-07-25","arxiv_id":"2207.12185","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-task-bert-model-for-schema-guided","slug":"a-multi-task-bert-model-for-schema-guided","title":"A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking","date":"2022-07-02","arxiv_id":"2207.00828","repositories_listed":1,"syntology":null},{"url":"/paper/learning-dialogue-representations-from","slug":"learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","repositories_listed":1,"syntology":null},{"url":"/paper/improving-zero-and-few-shot-generalization-in","slug":"improving-zero-and-few-shot-generalization-in","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","date":"2022-05-25","arxiv_id":"2205.12673","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/improving-zero-and-few-shot-generalization-in#ran","syntology_url":"https://syntology.ai/paper/2205.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12673"}},"official":{"repos":["prakharguptaz/Instructdial"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-augmented-data-selection-for-few-shot","slug":"self-augmented-data-selection-for-few-shot","title":"Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation","date":"2022-05-19","arxiv_id":"2205.09661","repositories_listed":1,"syntology":null},{"url":"/paper/empathetic-response-generation-with-state","slug":"empathetic-response-generation-with-state","title":"Empathetic Response Generation with State Management","date":"2022-05-07","arxiv_id":"2205.03676","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-meaning-representation-for-task","slug":"dialogue-meaning-representation-for-task","title":"Dialogue Meaning Representation for Task-Oriented Dialogue Systems","date":"2022-04-23","arxiv_id":"2204.10989","repositories_listed":1,"syntology":null},{"url":"/paper/converse-a-tree-based-modular-task-oriented","slug":"converse-a-tree-based-modular-task-oriented","title":"Converse: A Tree-Based Modular Task-Oriented Dialogue System","date":"2022-03-23","arxiv_id":"2203.12187","repositories_listed":1,"syntology":null},{"url":"/paper/a-slot-is-not-built-in-one-utterance-spoken-1","slug":"a-slot-is-not-built-in-one-utterance-spoken-1","title":"A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots","date":"2022-03-21","arxiv_id":"2203.10759","repositories_listed":1,"syntology":null},{"url":"/paper/an-interpretable-neuro-symbolic-reasoning","slug":"an-interpretable-neuro-symbolic-reasoning","title":"An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation","date":"2022-03-11","arxiv_id":"2203.05843","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-on-language-models-for-1","slug":"a-comparative-study-on-language-models-for-1","title":"A Comparative Study on Language Models for Task-Oriented Dialogue Systems","date":"2022-01-21","arxiv_id":"2201.08687","repositories_listed":1,"syntology":null},{"url":"/paper/unifiedskg-unifying-and-multi-tasking","slug":"unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","arxiv_id":"2201.05966","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifiedskg-unifying-and-multi-tasking#ran","syntology_url":"https://syntology.ai/paper/2201.05966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05966"}},"official":{"repos":["hkunlp/unifiedskg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/globalwoz-globalizing-multiwoz-to-develop-1","slug":"globalwoz-globalizing-multiwoz-to-develop-1","title":"GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/contextual-semantic-parsing-for-multilingual","slug":"contextual-semantic-parsing-for-multilingual","title":"Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues","date":"2021-11-04","arxiv_id":"2111.02574","repositories_listed":1,"syntology":null},{"url":"/paper/domain-lifelong-learning-for-dialogue-state","slug":"domain-lifelong-learning-for-dialogue-state","title":"Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gcdf1-a-goal-and-context-driven-f-score-for","slug":"gcdf1-a-goal-and-context-driven-f-score-for","title":"GCDF1: A Goal- and Context- Driven F-Score for Evaluating User Models","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/amendable-generation-for-dialogue-state","slug":"amendable-generation-for-dialogue-state","title":"Amendable Generation for Dialogue State Tracking","date":"2021-10-29","arxiv_id":"2110.15659","repositories_listed":1,"syntology":null},{"url":"/paper/globalwoz-globalizing-multiwoz-to-develop","slug":"globalwoz-globalizing-multiwoz-to-develop","title":"GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems","date":"2021-10-14","arxiv_id":"2110.07679","repositories_listed":1,"syntology":null},{"url":"/paper/how-robust-r-u-evaluating-task-oriented","slug":"how-robust-r-u-evaluating-task-oriented","title":"\"How Robust r u?\": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations","date":"2021-09-28","arxiv_id":"2109.13489","repositories_listed":1,"syntology":null},{"url":"/paper/towards-zero-and-few-shot-knowledge-seeking","slug":"towards-zero-and-few-shot-knowledge-seeking","title":"Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems","date":"2021-09-18","arxiv_id":"2109.08820","repositories_listed":1,"syntology":null},{"url":"/paper/emowoz-a-large-scale-corpus-and-labelling","slug":"emowoz-a-large-scale-corpus-and-labelling","title":"EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems","date":"2021-09-10","arxiv_id":"2109.04919","repositories_listed":1,"syntology":null},{"url":"/paper/a-template-guided-hybrid-pointer-network-for-1","slug":"a-template-guided-hybrid-pointer-network-for-1","title":"A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/space-efficient-context-encoding-for-non-task","slug":"space-efficient-context-encoding-for-non-task","title":"Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-template-guided-hybrid-pointer-network-for","slug":"a-template-guided-hybrid-pointer-network-for","title":"A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems","date":"2021-06-10","arxiv_id":"2106.05830","repositories_listed":1,"syntology":null},{"url":"/paper/shades-of-bleu-flavours-of-success-the-case","slug":"shades-of-bleu-flavours-of-success-the-case","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","date":"2021-06-10","arxiv_id":"2106.05555","repositories_listed":1,"syntology":null},{"url":"/paper/retrieve-memorize-dialog-policy-learning-with","slug":"retrieve-memorize-dialog-policy-learning-with","title":"Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory","date":"2021-06-04","arxiv_id":"2106.02317","repositories_listed":1,"syntology":null},{"url":"/paper/high-quality-diversification-for-task","slug":"high-quality-diversification-for-task","title":"High-Quality Diversification for Task-Oriented Dialogue Systems","date":"2021-06-02","arxiv_id":"2106.00891","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-study-how-the-context","slug":"comprehensive-study-how-the-context","title":"Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?","date":"2021-05-08","arxiv_id":"2105.03571","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-user-satisfaction-for-the","slug":"simulating-user-satisfaction-for-the","title":"Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems","date":"2021-05-08","arxiv_id":"2105.03748","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","repositories_listed":1,"syntology":null},{"url":"/paper/multiwoz-2-4-a-multi-domain-task-oriented","slug":"multiwoz-2-4-a-multi-domain-task-oriented","title":"MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation","date":"2021-04-01","arxiv_id":"2104.00773","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multiwoz-2-4-a-multi-domain-task-oriented#ran","syntology_url":"https://syntology.ai/paper/2104.00773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00773"}},"official":{"repos":["smartyfh/MultiWOZ2.4"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/a-cooperative-memory-network-for-personalized","slug":"a-cooperative-memory-network-for-personalized","title":"A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles","date":"2021-02-16","arxiv_id":"2102.08322","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-cross-lingual","slug":"an-empirical-study-of-cross-lingual","title":"An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker","date":"2021-01-27","arxiv_id":"2101.11360","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-domain-apis-task-oriented-1","slug":"beyond-domain-apis-task-oriented-1","title":"Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9","date":"2021-01-22","arxiv_id":"2101.09276","repositories_listed":1,"syntology":null},{"url":"/paper/slot-self-attentive-dialogue-state-tracking","slug":"slot-self-attentive-dialogue-state-tracking","title":"Slot Self-Attentive Dialogue State Tracking","date":"2021-01-22","arxiv_id":"2101.09374","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/slot-self-attentive-dialogue-state-tracking#ran","syntology_url":"https://syntology.ai/paper/2101.09374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.09374"}},"official":{"repos":["smartyfh/DST-STAR"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/continual-learning-in-task-oriented-dialogue","slug":"continual-learning-in-task-oriented-dialogue","title":"Continual Learning in Task-Oriented Dialogue Systems","date":"2020-12-31","arxiv_id":"2012.15504","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-retrieve-entity-aware-knowledge","slug":"learning-to-retrieve-entity-aware-knowledge","title":"Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems","date":"2020-12-22","arxiv_id":"2012.11937","repositories_listed":1,"syntology":null},{"url":"/paper/airconcierge-generating-task-oriented","slug":"airconcierge-generating-task-oriented","title":"AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval","date":"2020-11-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lava-latent-action-spaces-via-variational","slug":"lava-latent-action-spaces-via-variational","title":"LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization","date":"2020-11-18","arxiv_id":"2011.09378","repositories_listed":1,"syntology":null},{"url":"/paper/conditioned-text-generation-with-transfer-for","slug":"conditioned-text-generation-with-transfer-for","title":"Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems","date":"2020-11-03","arxiv_id":"2011.02143","repositories_listed":1,"syntology":null},{"url":"/paper/amalgamating-knowledge-from-two-teachers-for","slug":"amalgamating-knowledge-from-two-teachers-for","title":"Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adding-chit-chats-to-enhance-task-oriented","slug":"adding-chit-chats-to-enhance-task-oriented","title":"Adding Chit-Chat to Enhance Task-Oriented Dialogues","date":"2020-10-24","arxiv_id":"2010.12757","repositories_listed":1,"syntology":null}],"syntology_records":13,"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"},"key_notes":{"n_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'","n_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_where_code_ran":17,"papers_where_code_ran_first_page":"/task/task-oriented-dialogue-systems/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/task-oriented-dialogue-systems/papers/2","json":"/task/task-oriented-dialogue-systems/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/task-oriented-dialogue-systems/papers/3","json":"/task/task-oriented-dialogue-systems/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/task-oriented-dialogue-systems/papers/4","json":"/task/task-oriented-dialogue-systems/papers/4.json","rows":8},{"order":"ran","page":1,"of":1,"url":"/task/task-oriented-dialogue-systems/papers/ran/1","json":"/task/task-oriented-dialogue-systems/papers/ran/1.json","rows":17}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"424bd151cd5252c8361004129ddc330523bf8a72858800b87d6025869d0c4396","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}