{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/tapas-weakly-supervised-table-parsing-via-pre","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","arxiv_id":"2004.02349","date":"2020-04-05","proceeding":"ACL 2020 6","authors":["Jonathan Herzig","Paweł Krzysztof Nowak","Thomas Müller","Francesco Piccinno","Julian Martin Eisenschlos"],"abstract":"Answering natural language questions over tables is usually seen as a semantic parsing task. To alleviate the collection cost of full logical forms, one popular approach focuses on weak supervision consisting of denotations instead of logical forms. However, training semantic parsers from weak supervision poses difficulties, and in addition, the generated logical forms are only used as an intermediate step prior to retrieving the denotation. In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms. TAPAS trains from weak supervision, and predicts the denotation by selecting table cells and optionally applying a corresponding aggregation operator to such selection. TAPAS extends BERT's architecture to encode tables as input, initializes from an effective joint pre-training of text segments and tables crawled from Wikipedia, and is trained end-to-end. We experiment with three different semantic parsing datasets, and find that TAPAS outperforms or rivals semantic parsing models by improving state-of-the-art accuracy on SQA from 55.1 to 67.2 and performing on par with the state-of-the-art on WIKISQL and WIKITQ, but with a simpler model architecture. We additionally find that transfer learning, which is trivial in our setting, from WIKISQL to WIKITQ, yields 48.7 accuracy, 4.2 points above the state-of-the-art.","url_abs":"https://arxiv.org/abs/2004.02349v2","url_pdf":"https://arxiv.org/pdf/2004.02349v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/google-research/tapas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/PriyalNarang/Tapas-Experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/dreji18/Tapas-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/MindCode-4/code-5/tree/main/tapas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/MindSpore-scientific/code-7/tree/main/TAPAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/kamalkraj/TAPAS-TF2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tapas-weakly-supervised-table-parsing-via-pre","repo_url":"https://github.com/pwc-1/Paper-10/tree/main/tapas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"tapas","method_name":"TAPAS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-parsing-on-sqa","task":"Semantic Parsing","dataset":"SQA","model":"TAPAS-Large","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-parsing-on-wikisql-1","task":"Semantic Parsing","dataset":"WikiSQL","model":"TAPAS-Large (weak supervision)","rank_in_archive_order":5,"of":5,"metrics":{"Denotation accuracy (test)":"83.6"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-parsing-on-wikitablequestions","task":"Semantic Parsing","dataset":"WikiTableQuestions","model":"TAPAS-Large (pre-trained on SQA)","rank_in_archive_order":20,"of":22,"metrics":{"Accuracy (Dev)":"/","Accuracy (Test)":"48.8"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.02349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.02349"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dreji18/Tapas-Implementation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-5/tree/main/tapas","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/tapas","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PriyalNarang/Tapas-Experiments","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-10/tree/main/tapas","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-7/tree/main/TAPAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kamalkraj/TAPAS-TF2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":14},"by_repo_kind":{"listed":{"samples":14,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"86f83c07342e5a39","entry":"convert_to_float","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/text_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/text_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86f83c07342e5a39"}},{"code_sha256_prefix":"3afaf4fe080fb374","entry":"flatten","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/segmented_tensor.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/segmented_tensor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3afaf4fe080fb374"}},{"code_sha256_prefix":"5627e0c233b85bf2","entry":"gather","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/segmented_tensor.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/segmented_tensor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5627e0c233b85bf2"}},{"code_sha256_prefix":"44a49b752068dd08","entry":"gelu","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/tf_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/tf_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"44a49b752068dd08"}},{"code_sha256_prefix":"2bdc76acdd4efd43","entry":"get_answer_indexes","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/prediction_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/prediction_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2bdc76acdd4efd43"}},{"code_sha256_prefix":"2f4d3cb79e069b0d","entry":"get_correct_powerset","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/interpretation_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/interpretation_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f4d3cb79e069b0d"}},{"code_sha256_prefix":"d05bac24655b6e92","entry":"get_initializer","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/modeling.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d05bac24655b6e92"}},{"code_sha256_prefix":"0d68ef2cc5138081","entry":"get_mean_cell_probs","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/prediction_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/prediction_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d68ef2cc5138081"}},{"code_sha256_prefix":"cfe3053c233813ea","entry":"is_ordinal","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/number_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/number_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfe3053c233813ea"}},{"code_sha256_prefix":"8c8db6c2cff0952b","entry":"pack_inputs","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/tf_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/tf_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c8db6c2cff0952b"}},{"code_sha256_prefix":"4617c8d5aef65a35","entry":"range_index_map","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/segmented_tensor.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/segmented_tensor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4617c8d5aef65a35"}},{"code_sha256_prefix":"c2414a1393c4800e","entry":"swish","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/models/tf_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/tf_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2414a1393c4800e"}},{"code_sha256_prefix":"84b82f831409eb64","entry":"tokenize_string","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/text_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/text_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"84b82f831409eb64"}},{"code_sha256_prefix":"a266b518abe797d8","entry":"wtq_normalize","repo":"kamalkraj/TAPAS-TF2","repo_kind":"listed","path":"tapas/utils/text_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/utils/text_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a266b518abe797d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}