{"url":"/sota/intent-detection-on-atis","task":{"name":"Intent Detection","url":"/task/intent-detection","note":null},"dataset":{"name":"ATIS","url":null},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Intent Detection** is a task of determining the underlying purpose or goal behind a user's search query given a context. The task plays a significant role in search and recommendations. \r\nA traditional approach for intent detection implies using an intent detector model to classify user search query into predefined intent categories, given a context.\r\nOne of the key challenges of the task implies identifying user intents for cold-start sessions, i.e., search sessions initiated by a non-logged-in\r\nor unrecognized user.\r\n\r\n<span class=\"description-source\">Source: [Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers](https://arxiv.org/abs/2012.08777)</span>\r\n<span class=\"description-source\">","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":16,"rows_with_code":13,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Bi-model with decoder","metrics":{"Accuracy":"98.99"},"uses_additional_data":false,"paper_date":"2018-12-26","paper":"/paper/a-bi-model-based-rnn-semantic-frame-parsing","paper_url":"http://arxiv.org/abs/1812.10235v1","paper_title":"A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling","code":"https://github.com/ray075hl/Bi-Model-Intent-And-Slot","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Transformer-Capsule","metrics":{"Accuracy":"98.89"},"uses_additional_data":false,"paper_date":"2020-02-07","paper":"/paper/transformer-capsule-model-for-intent","paper_url":"https://www.aaai.org/Papers/AAAI/2020GB/SA-ObuchowskiA.549.pdf","paper_title":"Transformer-Capsule Model for Intent Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Attention Encoder-Decoder NN","metrics":{"Accuracy":"98.43"},"uses_additional_data":false,"paper_date":"2016-09-06","paper":"/paper/attention-based-recurrent-neural-network","paper_url":"http://arxiv.org/abs/1609.01454v1","paper_title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","code":"https://github.com/DSKSD/RNN-for-Joint-NLU","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"Joint model with recurrent slot label context","metrics":{"Accuracy":"98.40"},"uses_additional_data":false,"paper_date":"2016-09-06","paper":"/paper/joint-online-spoken-language-understanding","paper_url":"http://arxiv.org/abs/1609.01462v1","paper_title":"Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"CTRAN","metrics":{"Accuracy":"98.07"},"uses_additional_data":false,"paper_date":"2023-03-19","paper":"/paper/ctran-cnn-transformer-based-network-for","paper_url":"https://arxiv.org/abs/2303.10606v1","paper_title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","code":"https://github.com/rafiepour/CTran","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Joint BERT + CRF","metrics":{"Accuracy":"97.9"},"uses_additional_data":false,"paper_date":"2019-02-28","paper":"/paper/bert-for-joint-intent-classification-and-slot","paper_url":"http://arxiv.org/abs/1902.10909v1","paper_title":"BERT for Joint Intent Classification and Slot Filling","code":"https://github.com/monologg/JointBERT","n_code_links":16,"syntology":{"n_ran":9,"n_unverified":23,"n_samples":32,"n_pointer_only_licence":3}},{"rank_in_archive_order":7,"model":"SF-ID","metrics":{"Accuracy":"97.76"},"uses_additional_data":false,"paper_date":"2019-06-30","paper":"/paper/a-novel-bi-directional-interrelated-model-for","paper_url":"https://arxiv.org/abs/1907.00390v1","paper_title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","code":"https://github.com/ZephyrChenzf/SF-ID-Network-For-NLU","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"SF-ID (BLSTM) network","metrics":{"Accuracy":"97.76"},"uses_additional_data":false,"paper_date":"2019-06-30","paper":"/paper/a-novel-bi-directional-interrelated-model-for","paper_url":"https://arxiv.org/abs/1907.00390v1","paper_title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","code":"https://github.com/ZephyrChenzf/SF-ID-Network-For-NLU","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"Stack-Propagation (+BERT)","metrics":{"Accuracy":"97.50"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/a-stack-propagation-framework-with-token","paper_url":"https://arxiv.org/abs/1909.02188v1","paper_title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","code":"https://github.com/LeePleased/StackPropagation-SLU","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"Joint BERT","metrics":{"Accuracy":"97.5"},"uses_additional_data":false,"paper_date":"2019-02-28","paper":"/paper/bert-for-joint-intent-classification-and-slot","paper_url":"http://arxiv.org/abs/1902.10909v1","paper_title":"BERT for Joint Intent Classification and Slot Filling","code":"https://github.com/monologg/JointBERT","n_code_links":16,"syntology":{"n_ran":9,"n_unverified":23,"n_samples":32,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"JointBERT-CAE","metrics":{"Accuracy":"97.5"},"uses_additional_data":false,"paper_date":"2022-09-21","paper":"/paper/cae-mechanism-to-diminish-the-class","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-16210-7_12","paper_title":"CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task","code":"https://github.com/phuongnm94/JointBERT_CAE","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DELTA (BLSTM-CRF)","metrics":{"Accuracy":"97.40"},"uses_additional_data":false,"paper_date":"2019-08-02","paper":"/paper/delta-a-deep-learning-based-language","paper_url":"https://arxiv.org/abs/1908.01853v1","paper_title":"DELTA: A DEep learning based Language Technology plAtform","code":"https://github.com/didi/delta","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"AGIF","metrics":{"Accuracy":"97.1"},"uses_additional_data":false,"paper_date":"2020-04-21","paper":"/paper/td-gin-token-level-dynamic-graph-interactive","paper_url":"https://arxiv.org/abs/2004.10087v4","paper_title":"AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling","code":"https://github.com/LooperXX/AGIF","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"LIDSNet","metrics":{"Accuracy":"95.97"},"uses_additional_data":false,"paper_date":"2021-10-06","paper":"/paper/lidsnet-a-lightweight-on-device-intent","paper_url":"https://arxiv.org/abs/2110.15717v1","paper_title":"LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"Slot-Gated BLSTM with Attension","metrics":{"Accuracy":"93.6"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/slot-gated-modeling-for-joint-slot-filling","paper_url":"https://aclanthology.org/N18-2118","paper_title":"Slot-Gated Modeling for Joint Slot Filling and Intent Prediction","code":"https://github.com/MiuLab/SlotGated-SLU","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"Capsule-NLU","metrics":{"Accuracy":"0.95"},"uses_additional_data":false,"paper_date":"2018-12-22","paper":"/paper/joint-slot-filling-and-intent-detection-via","paper_url":"https://arxiv.org/abs/1812.09471v2","paper_title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","code":"https://github.com/czhang99/Capsule-NLU","n_code_links":3,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":11,"n_unverified":26,"n_samples":37,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":49,"n_samples":69,"n_pointer_only_licence":8,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}