{"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/dialogue-state-tracking","name":"Dialogue State Tracking","slug":"dialogue-state-tracking","description_markdown":"Dialogue state tacking consists of determining at each turn of a dialogue the\nfull representation of what the user wants at that point in the dialogue,\nwhich contains a goal constraint, a set of requested slots, and the user's dialogue act.","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":"archive_url"},"counts":{"papers_tagged":300,"papers_with_code":138,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":13,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/dialogue-state-tracking-on-wizard-of-oz","slug":"dialogue-state-tracking-on-wizard-of-oz","dataset":"Wizard-of-Oz","dataset_url":"/dataset/wizard-of-oz","rows_in_archive":10,"metrics":["Joint","Request"],"first_row_in_archive_order":{"model":"AG-DST","paper_title":"Amendable Generation for Dialogue State Tracking","paper_url":"/paper/amendable-generation-for-dialogue-state","paper_date":"2021-10-29","arxiv_id":"2110.15659","code_links":[{"title":"PaddlePaddle/Knover","url":"https://github.com/PaddlePaddle/Knover/tree/develop/projects/AG-DST"}],"syntology":null}},{"leaderboard":"/sota/dialogue-state-tracking-on-cosql","slug":"dialogue-state-tracking-on-cosql","dataset":"CoSQL","dataset_url":"/dataset/cosql","rows_in_archive":9,"metrics":["question match accuracy","interaction match accuracy"],"first_row_in_archive_order":{"model":"RASAT+PICARD","paper_title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","paper_url":"/paper/rasat-integrating-relational-structures-into","paper_date":"2022-05-14","arxiv_id":"2205.06983","code_links":[{"title":"lumia-group/rasat","url":"https://github.com/lumia-group/rasat"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rasat-integrating-relational-structures-into#ran","syntology_url":"https://syntology.ai/paper/2205.06983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06983"}},"official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/dialogue-state-tracking-on-second-dialogue","slug":"dialogue-state-tracking-on-second-dialogue","dataset":"Second dialogue state tracking challenge","dataset_url":"/dataset/dialogue-state-tracking-challenge","rows_in_archive":7,"metrics":["Joint","Area","Food","Price","Request"],"first_row_in_archive_order":{"model":"Seq2Seq-DU-w/oSchema","paper_title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","paper_url":"/paper/a-sequence-to-sequence-approach-to-dialogue","paper_date":"2020-11-18","arxiv_id":"2011.09553","code_links":[{"title":"sweetalyssum/Seq2Seq-DU","url":"https://github.com/sweetalyssum/Seq2Seq-DU"}],"syntology":null}},{"leaderboard":"/sota/dialogue-state-tracking-on-simmc2-0","slug":"dialogue-state-tracking-on-simmc2-0","dataset":"SIMMC2.0","dataset_url":"/dataset/simmc2-0","rows_in_archive":5,"metrics":["Act F1","Slot F1"],"first_row_in_archive_order":{"model":"PaCE","paper_title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","paper_url":"/paper/pace-unified-multi-modal-dialogue-pre","paper_date":"2023-05-24","arxiv_id":"2305.14839","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}],"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"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/dialogue-state-tracking-on-multiwoz-2-1","slug":"dialogue-state-tracking-on-multiwoz-2-1","dataset":"MULTIWOZ 2.1","dataset_url":"/dataset/multiwoz","rows_in_archive":4,"metrics":["Joint Acc","MultiWOZ (Joint Goal Acc)"],"first_row_in_archive_order":{"model":"DeepStruct multi-task w/ finetune","paper_title":"DeepStruct: Pretraining of Language Models for Structure Prediction","paper_url":"/paper/deepstruct-pretraining-of-language-models-for-1","paper_date":"2022-05-21","arxiv_id":"2205.10475","code_links":[{"title":"cgraywang/deepstruct","url":"https://github.com/cgraywang/deepstruct"}],"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepstruct-pretraining-of-language-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2205.10475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10475"}},"official":{"repos":["cgraywang/deepstruct"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/dialogue-state-tracking-on-mmconv","slug":"dialogue-state-tracking-on-mmconv","dataset":"MMConv","dataset_url":"/dataset/mmconv","rows_in_archive":2,"metrics":["Categorical Accuracy","Non-Categorical Accuracy","Overall"],"first_row_in_archive_order":{"model":"PaCE","paper_title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","paper_url":"/paper/pace-unified-multi-modal-dialogue-pre","paper_date":"2023-05-24","arxiv_id":"2305.14839","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}],"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"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/dialogue-state-tracking-on-multiwoz-2-2","slug":"dialogue-state-tracking-on-multiwoz-2-2","dataset":"MULTIWOZ 2.2","dataset_url":"/dataset/multiwoz","rows_in_archive":2,"metrics":["MultiWOZ (Joint Goal Acc)"],"first_row_in_archive_order":{"model":"SGP-DST (base)","paper_title":"Dialogue State Tracking with a Language Model using Schema-Driven Prompting","paper_url":"/paper/dialogue-state-tracking-with-a-language-model","paper_date":"2021-09-15","arxiv_id":"2109.07506","code_links":[{"title":"chiahsuan156/dst-as-prompting","url":"https://github.com/chiahsuan156/dst-as-prompting"}],"syntology":null}}],"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/cosql","name":"CoSQL","full_name":"Conversational Text-to-SQL Challenge","num_papers_in_archive":45},{"url":"/dataset/dialogue-state-tracking-challenge","name":"Dialogue State Tracking Challenge","full_name":"Dialogue State Tracking Challenge","num_papers_in_archive":33},{"url":"/dataset/wizard-of-oz","name":"Wizard-of-Oz","full_name":"","num_papers_in_archive":28},{"url":"/dataset/crosswoz","name":"CrossWOZ","full_name":"CrossWOZ","num_papers_in_archive":25},{"url":"/dataset/klue","name":"KLUE","full_name":"Korean Language Understanding Evaluation","num_papers_in_archive":21},{"url":"/dataset/taskmaster-1","name":"Taskmaster-1","full_name":"Taskmaster-1","num_papers_in_archive":19},{"url":"/dataset/simmc2-0","name":"SIMMC2.0","full_name":"","num_papers_in_archive":13},{"url":"/dataset/risawoz","name":"RiSAWOZ","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/mmconv","name":"MMConv","full_name":"","num_papers_in_archive":3},{"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/indirectrequests","name":"IndirectRequests","full_name":"IndirectRequests","num_papers_in_archive":0}],"subtasks":[],"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":3,"rows_per_page":100,"shown":100,"of":300,"of_with_code":138,"tagged_in_all":300,"counts":{"archive_papers_tagged":300,"with_a_code_link":138,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":300,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/multiwoz-21-multi-domain-dialogue-state","slug":"multiwoz-21-multi-domain-dialogue-state","title":"MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines","date":"2019-07-02","arxiv_id":"1907.01669","repositories_listed":6,"syntology":{"n":23,"n_ran":19,"n_constructed":0,"n_ran_checked":17,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multiwoz-21-multi-domain-dialogue-state#ran","syntology_url":"https://syntology.ai/paper/1907.01669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01669"}},"official":{"repos":["budzianowski/multiwoz"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/klue-korean-language-understanding-evaluation","slug":"klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","date":"2021-05-20","arxiv_id":"2105.09680","repositories_listed":4,"syntology":null},{"url":"/paper/towards-scalable-multi-domain-conversational","slug":"towards-scalable-multi-domain-conversational","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","date":"2019-09-12","arxiv_id":"1909.05855","repositories_listed":4,"syntology":null},{"url":"/paper/picard-parsing-incrementally-for-constrained","slug":"picard-parsing-incrementally-for-constrained","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","date":"2021-09-10","arxiv_id":"2109.05093","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/picard-parsing-incrementally-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2109.05093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05093"}},"official":{"repos":["ElementAI/picard"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/efficient-dialogue-state-tracking-by","slug":"efficient-dialogue-state-tracking-by","title":"Efficient Dialogue State Tracking by Selectively Overwriting Memory","date":"2019-11-10","arxiv_id":"1911.03906","repositories_listed":3,"syntology":null},{"url":"/paper/cosql-a-conversational-text-to-sql-challenge","slug":"cosql-a-conversational-text-to-sql-challenge","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","date":"2019-09-11","arxiv_id":"1909.05378","repositories_listed":3,"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":0,"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/cosql-a-conversational-text-to-sql-challenge#ran","syntology_url":"https://syntology.ai/paper/1909.05378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05378"}},"official":{"repos":["ryanzhumich/editsql"],"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/editing-based-sql-query-generation-for-cross","slug":"editing-based-sql-query-generation-for-cross","title":"Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions","date":"2019-09-02","arxiv_id":"1909.00786","repositories_listed":3,"syntology":null},{"url":"/paper/checkdst-measuring-real-world-generalization","slug":"checkdst-measuring-real-world-generalization","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","date":"2021-12-15","arxiv_id":"2112.08321","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-bot-prompt-based-learning-for","slug":"few-shot-bot-prompt-based-learning-for","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","date":"2021-10-15","arxiv_id":"2110.08118","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-bot-prompt-based-learning-for#ran","syntology_url":"https://syntology.ai/paper/2110.08118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08118"}},"official":{"repos":["andreamad8/FSB","tunib-ai/parallelformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-pre-training-for-plug-and-play","slug":"multi-task-pre-training-for-plug-and-play","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","date":"2021-09-29","arxiv_id":"2109.14739","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-pre-training-for-plug-and-play#ran","syntology_url":"https://syntology.ai/paper/2109.14739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14739"}},"official":{"repos":["awslabs/pptod"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-slot-descriptions-for-zero-shot","slug":"leveraging-slot-descriptions-for-zero-shot","title":"Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking","date":"2021-05-10","arxiv_id":"2105.04222","repositories_listed":2,"syntology":null},{"url":"/paper/structured-prediction-as-translation-between-1","slug":"structured-prediction-as-translation-between-1","title":"Structured Prediction as Translation between Augmented Natural Languages","date":"2021-01-14","arxiv_id":"2101.05779","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-hybrid-relation-network-for-cross","slug":"dynamic-hybrid-relation-network-for-cross","title":"Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing","date":"2021-01-05","arxiv_id":"2101.01686","repositories_listed":2,"syntology":null},{"url":"/paper/coco-controllable-counterfactuals-for-1","slug":"coco-controllable-counterfactuals-for-1","title":"CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers","date":"2020-10-24","arxiv_id":"2010.12850","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coco-controllable-counterfactuals-for-1#ran","syntology_url":"https://syntology.ai/paper/2010.12850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12850"}},"official":{"repos":["salesforce/coco-dst"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-domain-dialogue-state-tracking-a-purely","slug":"multi-domain-dialogue-state-tracking-a-purely","title":"Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking","date":"2020-10-24","arxiv_id":"2010.14061","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/schema-guided-dialogue-state-tracking-task-at","slug":"schema-guided-dialogue-state-tracking-task-at","title":"Schema-Guided Dialogue State Tracking Task at DSTC8","date":"2020-02-02","arxiv_id":"2002.01359","repositories_listed":2,"syntology":null},{"url":"/paper/multi-domain-dialogue-state-tracking-as","slug":"multi-domain-dialogue-state-tracking-as","title":"Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering","date":"2019-11-07","arxiv_id":"1911.06192","repositories_listed":2,"syntology":null},{"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/explicit-state-tracking-with-semi-supervision","slug":"explicit-state-tracking-with-semi-supervision","title":"Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation","date":"2018-08-31","arxiv_id":"1808.10596","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/semantic-specialisation-of-distributional","slug":"semantic-specialisation-of-distributional","title":"Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints","date":"2017-06-01","arxiv_id":"1706.00374","repositories_listed":2,"syntology":null},{"url":"/paper/counter-fitting-word-vectors-to-linguistic","slug":"counter-fitting-word-vectors-to-linguistic","title":"Counter-fitting Word Vectors to Linguistic Constraints","date":"2016-03-02","arxiv_id":"1603.00892","repositories_listed":2,"syntology":null},{"url":"/paper/towards-preventing-overreliance-on-task","slug":"towards-preventing-overreliance-on-task","title":"Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling","date":"2025-01-17","arxiv_id":"2501.10316","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-ontology-in-dialogue-state-tracking","slug":"beyond-ontology-in-dialogue-state-tracking","title":"Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot","date":"2024-10-30","arxiv_id":"2410.22767","repositories_listed":1,"syntology":null},{"url":"/paper/a-zero-shot-open-vocabulary-pipeline-for","slug":"a-zero-shot-open-vocabulary-pipeline-for","title":"A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding","date":"2024-09-24","arxiv_id":"2409.15861","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/continual-dialogue-state-tracking-via-reason","slug":"continual-dialogue-state-tracking-via-reason","title":"Continual Dialogue State Tracking via Reason-of-Select Distillation","date":"2024-08-19","arxiv_id":"2408.09846","repositories_listed":1,"syntology":null},{"url":"/paper/tasl-continual-dialog-state-tracking-via-task","slug":"tasl-continual-dialog-state-tracking-via-task","title":"TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation","date":"2024-08-19","arxiv_id":"2408.09857","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tasl-continual-dialog-state-tracking-via-task#ran","syntology_url":"https://syntology.ai/paper/2408.09857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09857"}},"official":{"repos":["WoodScene/TaSL"],"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"]}}},{"url":"/paper/multi-modal-dialogue-state-tracking-for","slug":"multi-modal-dialogue-state-tracking-for","title":"Multi-Modal Dialogue State Tracking for Playing GuessWhich Game","date":"2024-08-15","arxiv_id":"2408.08431","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21633","slug":"2407-21633","title":"Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation","date":"2024-07-31","arxiv_id":"2407.21633","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2407-21633#ran","syntology_url":"https://syntology.ai/paper/2407.21633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21633"}},"official":{"repos":["suntea233/duallora"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-two-dimensional-zero-shot-dialogue-state","slug":"a-two-dimensional-zero-shot-dialogue-state","title":"A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4","date":"2024-06-17","arxiv_id":"2406.11651","repositories_listed":1,"syntology":null},{"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/mope-mixture-of-prefix-experts-for-zero-shot","slug":"mope-mixture-of-prefix-experts-for-zero-shot","title":"MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking","date":"2024-04-12","arxiv_id":"2404.08559","repositories_listed":1,"syntology":null},{"url":"/paper/common-ground-tracking-in-multimodal-dialogue","slug":"common-ground-tracking-in-multimodal-dialogue","title":"Common Ground Tracking in Multimodal Dialogue","date":"2024-03-26","arxiv_id":"2403.17284","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/encode-once-and-decode-in-parallel-efficient","slug":"encode-once-and-decode-in-parallel-efficient","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","date":"2024-03-19","arxiv_id":"2403.13112","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-as-zero-shot-dialogue","slug":"large-language-models-as-zero-shot-dialogue","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","date":"2024-02-16","arxiv_id":"2402.10466","repositories_listed":1,"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/large-language-models-as-zero-shot-dialogue#ran","syntology_url":"https://syntology.ai/paper/2402.10466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10466"}},"official":{"repos":["facebookresearch/fnctod"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/state-value-generation-with-prompt-learning","slug":"state-value-generation-with-prompt-learning","title":"State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking","date":"2024-01-30","arxiv_id":"2401.16862","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/detecting-agreement-in-multi-party-dialogue","slug":"detecting-agreement-in-multi-party-dialogue","title":"Detecting agreement in multi-party dialogue: evaluating speaker diarisation versus a procedural baseline to enhance user engagement","date":"2023-11-06","arxiv_id":"2311.03021","repositories_listed":1,"syntology":null},{"url":"/paper/multi-user-multiwoz-task-oriented-dialogues","slug":"multi-user-multiwoz-task-oriented-dialogues","title":"Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users","date":"2023-10-31","arxiv_id":"2310.20479","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/semantic-parsing-by-large-language-models-for","slug":"semantic-parsing-by-large-language-models-for","title":"Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking","date":"2023-10-16","arxiv_id":"2310.10520","repositories_listed":1,"syntology":null},{"url":"/paper/uno-dst-leveraging-unlabelled-data-in-zero","slug":"uno-dst-leveraging-unlabelled-data-in-zero","title":"UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking","date":"2023-10-16","arxiv_id":"2310.10492","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/diverse-retrieval-augmented-in-context","slug":"diverse-retrieval-augmented-in-context","title":"Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking","date":"2023-07-04","arxiv_id":"2307.01453","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 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) · 2 unverified","sample_list":"/paper/diverse-retrieval-augmented-in-context#ran","syntology_url":"https://syntology.ai/paper/2307.01453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01453"}},"official":{"repos":["jlab-nlp/refpydst"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompter-zero-shot-adaptive-prefixes-for","slug":"prompter-zero-shot-adaptive-prefixes-for","title":"Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation","date":"2023-06-07","arxiv_id":"2306.04724","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-for-zero-shot-dialogue-state-tracking","slug":"chatgpt-for-zero-shot-dialogue-state-tracking","title":"ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?","date":"2023-06-02","arxiv_id":"2306.01386","repositories_listed":1,"syntology":null},{"url":"/paper/diable-efficient-dialogue-state-tracking-as","slug":"diable-efficient-dialogue-state-tracking-as","title":"Diable: Efficient Dialogue State Tracking as Operations on Tables","date":"2023-05-26","arxiv_id":"2305.17020","repositories_listed":1,"syntology":null},{"url":"/paper/pace-unified-multi-modal-dialogue-pre","slug":"pace-unified-multi-modal-dialogue-pre","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","date":"2023-05-24","arxiv_id":"2305.14839","repositories_listed":1,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/continual-dialogue-state-tracking-via-example","slug":"continual-dialogue-state-tracking-via-example","title":"Continual Dialogue State Tracking via Example-Guided Question Answering","date":"2023-05-23","arxiv_id":"2305.13721","repositories_listed":1,"syntology":null},{"url":"/paper/olisia-a-cascade-system-for-spoken-dialogue","slug":"olisia-a-cascade-system-for-spoken-dialogue","title":"OLISIA: a Cascade System for Spoken Dialogue State Tracking","date":"2023-04-20","arxiv_id":"2304.11073","repositories_listed":1,"syntology":null},{"url":"/paper/choice-fusion-as-knowledge-for-zero-shot","slug":"choice-fusion-as-knowledge-for-zero-shot","title":"Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking","date":"2023-02-25","arxiv_id":"2302.13013","repositories_listed":1,"syntology":null},{"url":"/paper/zero-and-few-shot-localization-of-task","slug":"zero-and-few-shot-localization-of-task","title":"Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation","date":"2023-02-18","arxiv_id":"2302.09424","repositories_listed":1,"syntology":null},{"url":"/paper/metaassist-robust-dialogue-state-tracking","slug":"metaassist-robust-dialogue-state-tracking","title":"MetaASSIST: Robust Dialogue State Tracking with Meta Learning","date":"2022-10-22","arxiv_id":"2210.12397","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/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/controllable-user-dialogue-act-augmentation","slug":"controllable-user-dialogue-act-augmentation","title":"Controllable User Dialogue Act Augmentation for Dialogue State Tracking","date":"2022-07-26","arxiv_id":"2207.12757","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/multimodal-dialogue-state-tracking-1","slug":"multimodal-dialogue-state-tracking-1","title":"Multimodal Dialogue State Tracking","date":"2022-06-16","arxiv_id":"2206.07898","repositories_listed":1,"syntology":null},{"url":"/paper/a-unifying-view-on-task-oriented-dialogue","slug":"a-unifying-view-on-task-oriented-dialogue","title":"A Unifying View On Task-oriented Dialogue Annotation","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deepstruct-pretraining-of-language-models-for-1","slug":"deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","arxiv_id":"2205.10475","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepstruct-pretraining-of-language-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2205.10475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10475"}},"official":{"repos":["cgraywang/deepstruct"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-the-granularity-multi-perspective-1","slug":"beyond-the-granularity-multi-perspective-1","title":"Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking","date":"2022-05-20","arxiv_id":"2205.10059","repositories_listed":1,"syntology":null},{"url":"/paper/rasat-integrating-relational-structures-into","slug":"rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","arxiv_id":"2205.06983","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rasat-integrating-relational-structures-into#ran","syntology_url":"https://syntology.ai/paper/2205.06983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06983"}},"official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/luna-learning-slot-turn-alignment-for","slug":"luna-learning-slot-turn-alignment-for","title":"LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking","date":"2022-05-05","arxiv_id":"2205.02550","repositories_listed":1,"syntology":null},{"url":"/paper/xqa-dst-multi-domain-and-multi-lingual-1","slug":"xqa-dst-multi-domain-and-multi-lingual-1","title":"XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking","date":"2022-04-12","arxiv_id":"2204.05895","repositories_listed":1,"syntology":null},{"url":"/paper/towards-fair-evaluation-of-dialogue-state","slug":"towards-fair-evaluation-of-dialogue-state","title":"Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances","date":"2022-04-07","arxiv_id":"2204.03375","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-learning-for-few-shot-dialogue","slug":"in-context-learning-for-few-shot-dialogue","title":"In-Context Learning for Few-Shot Dialogue State Tracking","date":"2022-03-16","arxiv_id":"2203.08568","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/in-context-learning-for-few-shot-dialogue#ran","syntology_url":"https://syntology.ai/paper/2203.08568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08568"}},"official":{"repos":["yushi-hu/ic-dst"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dialogue-summaries-as-dialogue-states-ds2","slug":"dialogue-summaries-as-dialogue-states-ds2","title":"Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking","date":"2022-03-03","arxiv_id":"2203.01552","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":15,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dialogue-summaries-as-dialogue-states-ds2#ran","syntology_url":"https://syntology.ai/paper/2203.01552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01552"}},"official":{"repos":["jshin49/ds2"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/assist-towards-label-noise-robust-dialogue-1","slug":"assist-towards-label-noise-robust-dialogue-1","title":"ASSIST: Towards Label Noise-Robust Dialogue State Tracking","date":"2022-02-26","arxiv_id":"2202.13024","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"8 ran (of which 6 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) · 2 unverified","sample_list":"/paper/assist-towards-label-noise-robust-dialogue-1#ran","syntology_url":"https://syntology.ai/paper/2202.13024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13024"}},"official":{"repos":["smartyfh/dst-assist"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-tracking-dialogue-state-by-inheriting-slot","slug":"on-tracking-dialogue-state-by-inheriting-slot","title":"On Tracking Dialogue State by Inheriting Slot Values in Mentioned Slot Pools","date":"2022-02-15","arxiv_id":"2202.07156","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/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/improving-dialogue-state-tracking-with-turn","slug":"improving-dialogue-state-tracking-with-turn","title":"Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation","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/sgd-x-a-benchmark-for-robust-generalization","slug":"sgd-x-a-benchmark-for-robust-generalization","title":"SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems","date":"2021-10-13","arxiv_id":"2110.06800","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-intermediate-fine-tuning","slug":"cross-lingual-intermediate-fine-tuning","title":"Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking","date":"2021-09-28","arxiv_id":"2109.13620","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/dialogue-state-tracking-with-a-language-model","slug":"dialogue-state-tracking-with-a-language-model","title":"Dialogue State Tracking with a Language Model using Schema-Driven Prompting","date":"2021-09-15","arxiv_id":"2109.07506","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-dialogue-state-tracking-via-cross","slug":"zero-shot-dialogue-state-tracking-via-cross","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","date":"2021-09-10","arxiv_id":"2109.04655","repositories_listed":1,"syntology":null},{"url":"/paper/effective-sequence-to-sequence-dialogue-state","slug":"effective-sequence-to-sequence-dialogue-state","title":"Effective Sequence-to-Sequence Dialogue State Tracking","date":"2021-08-31","arxiv_id":"2108.13990","repositories_listed":1,"syntology":null},{"url":"/paper/dual-slot-selector-via-local-reliability","slug":"dual-slot-selector-via-local-reliability","title":"Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking","date":"2021-07-27","arxiv_id":"2107.12578","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-state-tracking-with-multi-level","slug":"dialogue-state-tracking-with-multi-level","title":"Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations","date":"2021-07-12","arxiv_id":"2107.05168","repositories_listed":1,"syntology":null},{"url":"/paper/mconv-an-environment-for-multimodal","slug":"mconv-an-environment-for-multimodal","title":"MConv: An Environment for Multimodal Conversational Search across Multiple Domains","date":"2021-07-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hi-dst-a-hierarchical-approach-for-scalable","slug":"hi-dst-a-hierarchical-approach-for-scalable","title":"Hi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking","date":"2021-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-slot-descriptions-for-zero-shot-1","slug":"leveraging-slot-descriptions-for-zero-shot-1","title":"Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neuralwoz-learning-to-collect-task-oriented","slug":"neuralwoz-learning-to-collect-task-oriented","title":"NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation","date":"2021-05-30","arxiv_id":"2105.14454","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neuralwoz-learning-to-collect-task-oriented#ran","syntology_url":"https://syntology.ai/paper/2105.14454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14454"}},"official":{"repos":["naver-ai/neuralwoz"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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/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/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/few-shot-dialogue-state-tracking-using-meta","slug":"few-shot-dialogue-state-tracking-using-meta","title":"Few Shot Dialogue State Tracking using Meta-learning","date":"2021-01-17","arxiv_id":"2101.06779","repositories_listed":1,"syntology":null},{"url":"/paper/a-sequence-to-sequence-approach-to-dialogue","slug":"a-sequence-to-sequence-approach-to-dialogue","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","date":"2020-11-18","arxiv_id":"2011.09553","repositories_listed":1,"syntology":null},{"url":"/paper/nuanced-natural-utterance-annotation-for","slug":"nuanced-natural-utterance-annotation-for","title":"NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions","date":"2020-10-24","arxiv_id":"2010.12758","repositories_listed":1,"syntology":null}],"syntology_records":21,"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":26,"papers_where_code_ran_first_page":"/task/dialogue-state-tracking/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":3,"url":"/task/dialogue-state-tracking/papers/2","json":"/task/dialogue-state-tracking/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/dialogue-state-tracking/papers/3","json":"/task/dialogue-state-tracking/papers/3.json","rows":100},{"order":"ran","page":1,"of":1,"url":"/task/dialogue-state-tracking/papers/ran/1","json":"/task/dialogue-state-tracking/papers/ran/1.json","rows":26}],"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":"d5a1f25bc6512842ff6613dd06385beca4c09b8ca7405d6688705b2574634aef","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}