{"url":"/task/intent-classification","name":"Intent Classification","slug":"intent-classification","description_markdown":"**Intent Classification** is the task of correctly labeling a natural language utterance from a predetermined set of intents\r\n\r\n\r\n<span class=\"description-source\">Source: [Multi-Layer Ensembling Techniques for Multilingual Intent Classification ](https://arxiv.org/abs/1806.07914)</span>","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":344,"papers_with_code":113,"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":14,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/intent-classification-on-slurp","slug":"intent-classification-on-slurp","dataset":"SLURP","dataset_url":"/dataset/slurp","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"TDT 0-8","paper_title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","paper_url":"/paper/efficient-sequence-transduction-by-jointly","paper_date":"2023-04-13","arxiv_id":"2304.06795","code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"chimechallenge/C8DASR-Baseline-NeMo","url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo"},{"title":"kehanlu/Nemo","url":"https://github.com/kehanlu/Nemo"},{"title":"wd929/NeMo","url":"https://github.com/wd929/NeMo"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/intent-classification-on-massive","slug":"intent-classification-on-massive","dataset":"MASSIVE","dataset_url":"/dataset/massive","rows_in_archive":3,"metrics":["Intent Accuracy"],"first_row_in_archive_order":{"model":"mT5 Base (encoder-only)","paper_title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","paper_url":"/paper/massive-a-1m-example-multilingual-natural","paper_date":"2022-04-18","arxiv_id":"2204.08582","code_links":[{"title":"alexa/massive","url":"https://github.com/alexa/massive"},{"title":"pswietojanski/slurp","url":"https://github.com/pswietojanski/slurp"},{"title":"ai4bharat/indicbert","url":"https://github.com/ai4bharat/indicbert"},{"title":"hlt-mt/speech-massive","url":"https://github.com/hlt-mt/speech-massive"},{"title":"rita-nlp/italic","url":"https://github.com/rita-nlp/italic"},{"title":"robvanderg/sid4lr","url":"https://bitbucket.org/robvanderg/sid4lr"}],"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":1}}},{"leaderboard":"/sota/intent-classification-on-kuake-qic","slug":"intent-classification-on-kuake-qic","dataset":"KUAKE-QIC","dataset_url":"/dataset/kuake-qic","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RoBERTa-wwm-ext-base","paper_title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","paper_url":"/paper/cblue-a-chinese-biomedical-language","paper_date":"2021-06-15","arxiv_id":"2106.08087","code_links":[{"title":"cbluebenchmark/cblue","url":"https://github.com/cbluebenchmark/cblue"},{"title":"freedomintelligence/sdak","url":"https://github.com/freedomintelligence/sdak"}],"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}}},{"leaderboard":"/sota/intent-classification-on-orcas-i","slug":"intent-classification-on-orcas-i","dataset":"ORCAS-I","dataset_url":"/dataset/orcas-i","rows_in_archive":1,"metrics":["F1-score","Precision","Recall"],"first_row_in_archive_order":{"model":"BERT (query + URL)","paper_title":"ORCAS-I: Queries Annotated with Intent using Weak Supervision","paper_url":"/paper/orcas-i-queries-annotated-with-intent-using","paper_date":"2022-05-02","arxiv_id":"2205.00926","code_links":[{"title":"projectdossier/intents_labelling","url":"https://github.com/projectdossier/intents_labelling"}],"syntology":null}}],"datasets":[{"url":"/dataset/slurp","name":"SLURP","full_name":"Spoken Language Understanding Resource Package","num_papers_in_archive":106},{"url":"/dataset/clinc150","name":"CLINC150","full_name":"CLINC150","num_papers_in_archive":87},{"url":"/dataset/massive","name":"MASSIVE","full_name":"","num_papers_in_archive":72},{"url":"/dataset/xsid","name":"xSID","full_name":"Cross-lingual Slot and Intent Detection","num_papers_in_archive":18},{"url":"/dataset/kuake-qic","name":"KUAKE-QIC","full_name":"Query Intent Classification Dataset","num_papers_in_archive":14},{"url":"/dataset/banking77-oos","name":"BANKING77-OOS","full_name":"","num_papers_in_archive":6},{"url":"/dataset/clinc-single-domain-oos","name":"CLINC-Single-Domain-OOS","full_name":"","num_papers_in_archive":3},{"url":"/dataset/vimq","name":"ViMQ","full_name":"","num_papers_in_archive":3},{"url":"/dataset/arxivedits","name":"arXivEdits","full_name":"","num_papers_in_archive":2},{"url":"/dataset/orcas-i","name":"ORCAS-I","full_name":"Queries Annotated with Intent using Weak Supervision","num_papers_in_archive":2},{"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/mipd","name":"MIPD","full_name":"Manipulation and Intention In a Novel Corpus of Polish Disinformation","num_papers_in_archive":1},{"url":"/dataset/search4code","name":"Search4Code","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/skit-s2i","name":"Skit-S2I","full_name":"Skit-S2I: An Indian Accented Speech to Intent dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":113,"tagged_in_all":344,"items":[{"url":"/paper/bert-for-joint-intent-classification-and-slot","title":"BERT for Joint Intent Classification and Slot Filling","date":"2019-02-28","arxiv_id":"1902.10909","repositories_listed":16,"syntology":{"n":32,"n_ran":9,"n_unverified":23,"n_pointer_only":3}},{"url":"/paper/benchmarking-natural-language-understanding","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","date":"2019-03-13","arxiv_id":"1903.05566","repositories_listed":9,"syntology":null},{"url":"/paper/massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","arxiv_id":"2204.08582","repositories_listed":6,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/attention-based-recurrent-neural-network","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","date":"2016-09-06","arxiv_id":"1609.01454","repositories_listed":6,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":2}},{"url":"/paper/convert-efficient-and-accurate-conversational","title":"ConveRT: Efficient and Accurate Conversational Representations from Transformers","date":"2019-11-09","arxiv_id":"1911.03688","repositories_listed":5,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/an-evaluation-dataset-for-intent","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","date":"2019-09-04","arxiv_id":"1909.02027","repositories_listed":5,"syntology":null},{"url":"/paper/few-shot-text-classification-with-induction","title":"Induction Networks for Few-Shot Text Classification","date":"2019-02-27","arxiv_id":"1902.10482","repositories_listed":5,"syntology":null},{"url":"/paper/efficient-sequence-transduction-by-jointly","title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","date":"2023-04-13","arxiv_id":"2304.06795","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/end-to-end-slot-alignment-and-recognition-for","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","date":"2020-04-29","arxiv_id":"2004.14353","repositories_listed":3,"syntology":null},{"url":"/paper/subword-semantic-hashing-for-intent","title":"Subword Semantic Hashing for Intent Classification on Small Datasets","date":"2018-10-16","arxiv_id":"1810.07150","repositories_listed":3,"syntology":null},{"url":"/paper/learn-or-recall-revisiting-incremental","title":"Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models","date":"2023-12-13","arxiv_id":"2312.07887","repositories_listed":2,"syntology":null},{"url":"/paper/chatgpt-to-replace-crowdsourcing-of","title":"ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness","date":"2023-05-22","arxiv_id":"2305.12947","repositories_listed":2,"syntology":null},{"url":"/paper/z-bert-a-a-zero-shot-pipeline-for-unknown","title":"Z-BERT-A: a zero-shot Pipeline for Unknown Intent detection","date":"2022-08-15","arxiv_id":"2208.07084","repositories_listed":2,"syntology":null},{"url":"/paper/finstreder-simple-and-fast-spoken-language","title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","date":"2022-06-29","arxiv_id":"2206.14589","repositories_listed":2,"syntology":null},{"url":"/paper/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":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/cape-context-aware-private-embeddings-for","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","date":"2021-08-27","arxiv_id":"2108.12318","repositories_listed":2,"syntology":null},{"url":"/paper/cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","arxiv_id":"2106.08087","repositories_listed":2,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/from-masked-language-modeling-to-translation","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","date":"2021-05-15","arxiv_id":"2105.07316","repositories_listed":2,"syntology":null},{"url":"/paper/diverse-few-shot-text-classification-with","title":"Diverse Few-Shot Text Classification with Multiple Metrics","date":"2018-05-19","arxiv_id":"1805.07513","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-first-evaluation-of-chinese-human","title":"The First Evaluation of Chinese Human-Computer Dialogue Technology","date":"2017-09-29","arxiv_id":"1709.10217","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-gans-for-citation-intent","title":"Leveraging GANs for citation intent classification and its impact on citation network analysis","date":"2025-05-27","arxiv_id":"2505.21162","repositories_listed":1,"syntology":null},{"url":"/paper/testnuc-enhancing-test-time-computing","title":"TestNUC: Enhancing Test-Time Computing Approaches through Neighboring Unlabeled Data Consistency","date":"2025-02-26","arxiv_id":"2502.19163","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","repositories_listed":1,"syntology":null},{"url":"/paper/joint-automatic-speech-recognition-and","title":"Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding","date":"2025-01-13","arxiv_id":"2501.07329","repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-slu-a-massively-multilingual-benchmark","title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","date":"2025-01-10","arxiv_id":"2501.06117","repositories_listed":1,"syntology":null},{"url":"/paper/improving-dialectal-slot-and-intent-detection","title":"Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study","date":"2025-01-07","arxiv_id":"2501.03863","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-open-intent-classification","title":"Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision Boundary","date":"2024-12-18","arxiv_id":"2412.13542","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-user-intents-and-musical","title":"Predicting User Intents and Musical Attributes from Music Discovery Conversations","date":"2024-11-19","arxiv_id":"2411.12254","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-approach-for-fine-tuning-sentence","title":"A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks","date":"2024-10-17","arxiv_id":"2410.13649","repositories_listed":1,"syntology":null},{"url":"/paper/are-large-language-models-good-classifiers-a","title":"Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions","date":"2024-10-02","arxiv_id":"2410.02028","repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}