{"url":"/task/slot-filling","name":"Slot Filling","slug":"slot-filling","description_markdown":"The goal of **Slot Filling** is to identify from a running dialog different slots, which correspond to different parameters of the user’s query. For instance, when a user queries for nearby restaurants, key slots for location and preferred food are required for a dialog system to retrieve the appropriate information. Thus, the main challenge in the slot-filling task is to extract the target entity.\r\n\r\n\r\n<span class=\"description-source\">Source: [Real-time On-Demand Crowd-powered Entity Extraction ](https://arxiv.org/abs/1704.03627)</span>\r\n\r\nImage credit: [Robust Retrieval Augmented Generation for Zero-shot Slot Filling](https://arxiv.org/pdf/2108.13934.pdf)","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":458,"papers_with_code":140,"benchmarks":14,"benchmark_tables_in_archive":14,"benchmark_tables_shown":14,"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":27,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/slot-filling-on-kilt-zero-shot-re","slug":"slot-filling-on-kilt-zero-shot-re","dataset":"KILT: Zero Shot RE","dataset_url":"/dataset/kilt","rows_in_archive":21,"metrics":["KILT-AC","R-Prec","Recall@5","Accuracy","F1","KILT-F1"],"first_row_in_archive_order":{"model":"single ngram","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-kilt-t-rex","slug":"slot-filling-on-kilt-t-rex","dataset":"KILT: T-REx","dataset_url":"/dataset/kilt","rows_in_archive":20,"metrics":["KILT-AC","R-Prec","Recall@5","Accuracy","F1","KILT-F1"],"first_row_in_archive_order":{"model":"Re2G","paper_title":"Re2G: Retrieve, Rerank, Generate","paper_url":"/paper/re2g-retrieve-rerank-generate-2","paper_date":"2022-07-13","arxiv_id":"2207.06300","code_links":[{"title":"ibm/kgi-slot-filling","url":"https://github.com/ibm/kgi-slot-filling"}],"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/slot-filling-on-mixsnips","slug":"slot-filling-on-mixsnips","dataset":"MixSNIPS","dataset_url":"/dataset/mixsnips","rows_in_archive":16,"metrics":["Micro F1"],"first_row_in_archive_order":{"model":"BiSLU","paper_title":"Joint Multiple Intent Detection and Slot Filling with Supervised Contrastive Learning and Self-Distillation","paper_url":"/paper/joint-multiple-intent-detection-and-slot-2","paper_date":"2023-08-28","arxiv_id":"2308.14654","code_links":[{"title":"anhtunguyen98/bislu","url":"https://github.com/anhtunguyen98/bislu"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-mixatis","slug":"slot-filling-on-mixatis","dataset":"MixATIS","dataset_url":"/dataset/mixatis","rows_in_archive":15,"metrics":["Micro F1"],"first_row_in_archive_order":{"model":"MISCA","paper_title":"MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention","paper_url":"/paper/misca-a-joint-model-for-multiple-intent","paper_date":"2023-12-10","arxiv_id":"2312.05741","code_links":[{"title":"vinairesearch/misca","url":"https://github.com/vinairesearch/misca"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-atis","slug":"slot-filling-on-atis","dataset":"ATIS","dataset_url":null,"rows_in_archive":14,"metrics":["F1"],"first_row_in_archive_order":{"model":"CTRAN","paper_title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","paper_url":"/paper/ctran-cnn-transformer-based-network-for","paper_date":"2023-03-19","arxiv_id":"2303.10606","code_links":[{"title":"rafiepour/CTran","url":"https://github.com/rafiepour/CTran"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-snips","slug":"slot-filling-on-snips","dataset":"SNIPS","dataset_url":"/dataset/snips","rows_in_archive":10,"metrics":["F1","F1 (1-shot) avg","F1 (5-shot) avg"],"first_row_in_archive_order":{"model":"CTRAN","paper_title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","paper_url":"/paper/ctran-cnn-transformer-based-network-for","paper_date":"2023-03-19","arxiv_id":"2303.10606","code_links":[{"title":"rafiepour/CTran","url":"https://github.com/rafiepour/CTran"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-slurp","slug":"slot-filling-on-slurp","dataset":"SLURP","dataset_url":"/dataset/slurp","rows_in_archive":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"TDT 0-6","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/slot-filling-on-massive","slug":"slot-filling-on-massive","dataset":"MASSIVE","dataset_url":"/dataset/massive","rows_in_archive":3,"metrics":["Slot F1 Score"],"first_row_in_archive_order":{"model":"XLM-R Base","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/slot-filling-on-cais","slug":"slot-filling-on-cais","dataset":"CAIS","dataset_url":"/dataset/cais","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"CM-Net","paper_title":"CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding","paper_url":"/paper/cm-net-a-novel-collaborative-memory-network","paper_date":"2019-09-16","arxiv_id":"1909.06937","code_links":[{"title":"Adaxry/CM-Net","url":"https://github.com/Adaxry/CM-Net"},{"title":"1053399472/CAISandSMP","url":"https://github.com/1053399472/CAISandSMP"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-dialogue-state-tracking","slug":"slot-filling-on-dialogue-state-tracking","dataset":"Dialogue State Tracking Challenge","dataset_url":"/dataset/dialogue-state-tracking-challenge","rows_in_archive":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"MIDAS","paper_title":"MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU","paper_url":"/paper/midas-multi-level-intent-domain-and-slot","paper_date":"2024-08-15","arxiv_id":"2408.08144","code_links":[{"title":"adlnlp/Midas","url":"https://github.com/adlnlp/Midas"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-multiwoz-2-2","slug":"slot-filling-on-multiwoz-2-2","dataset":"MULTIWOZ 2.2","dataset_url":"/dataset/multiwoz","rows_in_archive":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"MIDAS","paper_title":"MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU","paper_url":"/paper/midas-multi-level-intent-domain-and-slot","paper_date":"2024-08-15","arxiv_id":"2408.08144","code_links":[{"title":"adlnlp/Midas","url":"https://github.com/adlnlp/Midas"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-polyvore","slug":"slot-filling-on-polyvore","dataset":"Polyvore","dataset_url":"/dataset/polyvore","rows_in_archive":1,"metrics":["FITB"],"first_row_in_archive_order":{"model":"Fashion GAE","paper_title":"Context-Aware Visual Compatibility Prediction","paper_url":"/paper/context-aware-visual-compatibility-prediction","paper_date":"2019-02-10","arxiv_id":"1902.03646","code_links":[{"title":"gcucurull/visual-compatibility","url":"https://github.com/gcucurull/visual-compatibility"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-proslu","slug":"slot-filling-on-proslu","dataset":"ProSLU","dataset_url":"/dataset/proslu","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"General SLU Model w/ Profile","paper_title":"Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding","paper_url":"/paper/text-is-no-more-enough-a-benchmark-for","paper_date":"2021-12-22","arxiv_id":"2112.11953","code_links":[{"title":"looperxx/proslu","url":"https://github.com/looperxx/proslu"}],"syntology":null}},{"leaderboard":"/sota/slot-filling-on-vietnamese-intent-detection","slug":"slot-filling-on-vietnamese-intent-detection","dataset":"ATIS (vi)","dataset_url":"/dataset/vietnamese-intent-detection-and-slot-filling","rows_in_archive":1,"metrics":["Slot F1"],"first_row_in_archive_order":{"model":"JointBERT-CAE","paper_title":"CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task","paper_url":"/paper/cae-mechanism-to-diminish-the-class","paper_date":"2022-09-21","arxiv_id":null,"code_links":[{"title":"phuongnm94/JointBERT_CAE","url":"https://github.com/phuongnm94/JointBERT_CAE"}],"syntology":null}}],"datasets":[{"url":"/dataset/multiwoz","name":"MultiWOZ","full_name":"Multi-domain Wizard-of-Oz","num_papers_in_archive":328},{"url":"/dataset/snips","name":"SNIPS","full_name":"SNIPS Natural Language Understanding benchmark","num_papers_in_archive":256},{"url":"/dataset/sgd","name":"SGD","full_name":"Schema-Guided Dialogue","num_papers_in_archive":186},{"url":"/dataset/kilt","name":"KILT","full_name":"KILT Benchmark","num_papers_in_archive":117},{"url":"/dataset/slurp","name":"SLURP","full_name":"Spoken Language Understanding Resource Package","num_papers_in_archive":106},{"url":"/dataset/massive","name":"MASSIVE","full_name":"","num_papers_in_archive":72},{"url":"/dataset/polyvore","name":"Polyvore","full_name":"Polyvore Outfits","num_papers_in_archive":62},{"url":"/dataset/dialogue-state-tracking-challenge","name":"Dialogue State Tracking Challenge","full_name":"Dialogue State Tracking Challenge","num_papers_in_archive":33},{"url":"/dataset/mixatis","name":"MixATIS","full_name":"","num_papers_in_archive":28},{"url":"/dataset/mixsnips","name":"MixSNIPS","full_name":"","num_papers_in_archive":26},{"url":"/dataset/xsid","name":"xSID","full_name":"Cross-lingual Slot and Intent Detection","num_papers_in_archive":18},{"url":"/dataset/cais","name":"CAIS","full_name":"Chinese Artificial Intelligence Speakers","num_papers_in_archive":6},{"url":"/dataset/media","name":"MEDIA","full_name":"MEDIA","num_papers_in_archive":6},{"url":"/dataset/risawoz","name":"RiSAWOZ","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/vietnamese-intent-detection-and-slot-filling","name":"ATIS (vi)","full_name":"Vietnamese Intent Detection and Slot Filling","num_papers_in_archive":4},{"url":"/dataset/multisubs","name":"MultiSubs","full_name":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","num_papers_in_archive":4},{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","num_papers_in_archive":2},{"url":"/dataset/pioner","name":"pioNER","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/proslu","name":"ProSLU","full_name":"Profile-based Spoken Language Understanding","num_papers_in_archive":2},{"url":"/dataset/spades","name":"Spades","full_name":"Semantic PArsing of DEclarative Sentences","num_papers_in_archive":2},{"url":"/dataset/careercoach-2022","name":"CareerCoach 2022","full_name":"","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/nomusic","name":"NoMusic","full_name":"","num_papers_in_archive":1},{"url":"/dataset/turkqa","name":"TurkQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/voice-navigation","name":"Voice Navigation","full_name":"","num_papers_in_archive":1},{"url":"/dataset/indirectrequests","name":"IndirectRequests","full_name":"IndirectRequests","num_papers_in_archive":0},{"url":"/dataset/noise-sf","name":"Noise-SF","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/extracting-covid-19-events-from-twitter","name":"Extracting COVID-19 Events from Twitter"},{"url":"/task/zero-shot-slot-filling","name":"Zero-shot Slot Filling"}],"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":140,"tagged_in_all":458,"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/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/learning-end-to-end-goal-oriented-dialog","title":"Learning End-to-End Goal-Oriented Dialog","date":"2016-05-24","arxiv_id":"1605.07683","repositories_listed":6,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"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/learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","repositories_listed":4,"syntology":null},{"url":"/paper/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/data-programming-creating-large-training-sets","title":"Data Programming: Creating Large Training Sets, Quickly","date":"2016-05-25","arxiv_id":"1605.07723","repositories_listed":4,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/joint-slot-filling-and-intent-detection-via","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","date":"2018-12-22","arxiv_id":"1812.09471","repositories_listed":3,"syntology":null},{"url":"/paper/a-persian-benchmark-for-joint-intent","title":"A Persian Benchmark for Joint Intent Detection and Slot Filling","date":"2023-03-01","arxiv_id":"2303.00408","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/call-larisa-ivanovna-code-switching-fools","title":"Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models","date":"2021-09-29","arxiv_id":"2109.14350","repositories_listed":2,"syntology":null},{"url":"/paper/slot-filling-for-biomedical-information","title":"Slot Filling for Biomedical Information Extraction","date":"2021-09-17","arxiv_id":"2109.08564","repositories_listed":2,"syntology":null},{"url":"/paper/robust-retrieval-augmented-generation-for","title":"Robust Retrieval Augmented Generation for Zero-shot Slot Filling","date":"2021-08-31","arxiv_id":"2108.13934","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"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/zero-shot-slot-filling-with-dpr-and-rag","title":"Zero-shot Slot Filling with DPR and RAG","date":"2021-04-17","arxiv_id":"2104.08610","repositories_listed":2,"syntology":null},{"url":"/paper/extracting-covid-19-events-from-twitter","title":"Extracting a Knowledge Base of COVID-19 Events from Social Media","date":"2020-06-03","arxiv_id":"2006.02567","repositories_listed":2,"syntology":null},{"url":"/paper/cm-net-a-novel-collaborative-memory-network","title":"CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding","date":"2019-09-16","arxiv_id":"1909.06937","repositories_listed":2,"syntology":null},{"url":"/paper/a-stack-propagation-framework-with-token","title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","date":"2019-09-05","arxiv_id":"1909.02188","repositories_listed":2,"syntology":null},{"url":"/paper/delta-a-deep-learning-based-language","title":"DELTA: A DEep learning based Language Technology plAtform","date":"2019-08-02","arxiv_id":"1908.01853","repositories_listed":2,"syntology":null},{"url":"/paper/a-novel-bi-directional-interrelated-model-for","title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","date":"2019-06-30","arxiv_id":"1907.00390","repositories_listed":2,"syntology":null},{"url":"/paper/slot-gated-modeling-for-joint-slot-filling","title":"Slot-Gated Modeling for Joint Slot Filling and Intent Prediction","date":"2018-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/position-aware-attention-and-supervised-data","title":"Position-aware Attention and Supervised Data Improve Slot Filling","date":"2017-09-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-relation-extraction-via-reading","title":"Zero-Shot Relation Extraction via Reading Comprehension","date":"2017-06-13","arxiv_id":"1706.04115","repositories_listed":2,"syntology":null},{"url":"/paper/a-knowledge-grounded-neural-conversation","title":"A Knowledge-Grounded Neural Conversation Model","date":"2017-02-07","arxiv_id":"1702.01932","repositories_listed":2,"syntology":null},{"url":"/paper/middle-layer-representation-alignment-for","title":"Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs","date":"2025-02-20","arxiv_id":"2502.14830","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"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/midas-multi-level-intent-domain-and-slot","title":"MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU","date":"2024-08-15","arxiv_id":"2408.08144","repositories_listed":1,"syntology":null},{"url":"/paper/speech-massive-a-multilingual-speech-dataset","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","date":"2024-08-07","arxiv_id":"2408.03900","repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}