{"url":"/method/tapas","slug":"tapas","name":"TAPAS","full_name":"TAPAS","full_name_withheld":false,"description_markdown":"**TAPAS** is a weakly supervised question answering model that reasons over tables without generating logical forms. TAPAS predicts a minimal program by selecting a subset of the table cells and a possible aggregation operation to be executed on top of them. Consequently, TAPAS can learn operations from natural language, without the need to specify them in some formalism. This is implemented by extending [BERT](https://paperswithcode.com/method/bert)’s architecture with additional embeddings that capture tabular structure, and with two classification layers for selecting cells and predicting a corresponding aggregation operator.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2004.02349v2","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Table Question Answering Models","url":"/methods/category/table-question-answering-models","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms","date":"2025-01-05","arxiv_id":"2501.02600","n_code_links":0,"syntology":null},{"paper":"/paper/qatch-benchmarking-sql-centric-tasks-with","title":"QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables","date":"2023-09-20","arxiv_id":"2309.11049","n_code_links":0,"syntology":null},{"paper":"/paper/tapas-a-toolbox-for-adversarial-privacy","title":"TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data","date":"2022-11-12","arxiv_id":"2211.06550","n_code_links":3,"syntology":{"ran":6,"of":11,"unverified":5,"pointer_only":0}},{"paper":null,"title":"Table-To-Text generation and pre-training with TabT5","date":"2022-10-17","arxiv_id":"2210.09162","n_code_links":0,"syntology":null},{"paper":"/paper/attestable-at-semeval-2021-task-9-extending","title":"AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/volta-at-semeval-2021-task-9-statement","title":"Volta at SemEval-2021 Task 9: Statement Verification and Evidence Finding with Tables using TAPAS and Transfer Learning","date":"2021-06-01","arxiv_id":"2106.00248","n_code_links":1,"syntology":null},{"paper":null,"title":"TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training","date":"2021-04-02","arxiv_id":"2104.01099","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-tables-with-intermediate-pre","title":"Understanding tables with intermediate pre-training","date":"2020-10-01","arxiv_id":"2010.00571","n_code_links":1,"syntology":null},{"paper":"/paper/tapas-weakly-supervised-table-parsing-via-pre","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","date":"2020-04-05","arxiv_id":"2004.02349","n_code_links":8,"syntology":{"ran":0,"of":14,"unverified":14,"pointer_only":0}}],"papers_shown":10,"tasks":[{"task":"/task/binary-classification","name":"Binary Classification","papers":2},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":2},{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":"/task/table-based-fact-verification","name":"Table-based Fact Verification","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/data-to-text-generation","name":"Data-to-Text Generation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/fact-checking","name":"Fact Checking","papers":1},{"task":"/task/fact-verification","name":"Fact Verification","papers":1},{"task":"/task/form","name":"Form","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":1},{"task":"/task/logical-reasoning","name":"Logical Reasoning","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/scheduling","name":"Scheduling","papers":1},{"task":"/task/semantic-parsing","name":"Semantic Parsing","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/tag","name":"TAG","papers":1}],"tasks_shown":20,"n_tasks":22,"usage_by_year":[{"year":"2020","papers":2},{"year":"2021","papers":3},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2025","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/tapas"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}