Papers › TAPAS: Weakly Supervised Table Parsing via Pre-training

TAPAS: Weakly Supervised Table Parsing via Pre-training

5 Apr 2020ACL 2020 6arXiv:2004.02349archive 2025-07-28

Jonathan Herzig, Paweł Krzysztof Nowak, Thomas Müller, Francesco Piccinno, Julian Martin Eisenschlos

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (google-research/tapas) is linked to this paper; the 14 samples below come from 1 community repository. Syntology harvested code from google-research/tapas for 2 other papers.

google-research/tapas: Syntology's graph links these samples to DoT: An efficient Double Transformer for NLP tasks with tables (arXiv:2106.00479; that paper's own run record: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified) and TableFormer: Robust Transformer Modeling for Table-Text Encoding (arXiv:2203.00274; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 14 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 14 samples from 1 repository, 14 ran (14 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/tapas officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DoT: An efficient Double Transformer for NLP tasks with tables (arXiv:2106.00479; that paper's own run record: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified) and TableFormer: Robust Transformer Modeling for Table-Text Encoding (arXiv:2203.00274; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
PriyalNarang/Tapas-Experiments mentioned on GitHubApache-2.0Syntology: not harvested report
dreji18/Tapas-Implementation mentioned on GitHubSyntology: not harvested report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MindCode-4/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTamin: Designing Scalable Vision Models in the Vision-Language Era (arXiv:2404.02132; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-7 Syntology: not harvested report
kamalkraj/TAPAS-TF2 tfApache-2.0Syntology: 14 samples, 14 ran (0 instrument-failed) · 0 unverified report
pwc-1/Paper-10 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large... (arXiv:2403.07714; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from kamalkraj/TAPAS-TF2. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

kamalkraj/TAPAS-TF2 community (archive-listed) 14 samples, 14 ran (0 instrument-failed) · 0 unverified
convert_to_float in 13 papers tapas/utils/text_utils.py ran Apache-2.0 (permissive) · 86f83c07342e5a39 · report fixture: signature value:str/0/str · returned float · level recorded 2026-09-24
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
tapas/models/segmented_tensor.py ran Apache-2.0 (permissive) · 3afaf4fe080fb374 · report fixture: signature index:IndexMap/0/?, name:str/0/str · returned IndexMap · level recorded 2026-09-24
gather in 75 papers tapas/models/segmented_tensor.py ran Apache-2.0 (permissive) · 5627e0c233b85bf2 · report fixture: signature values:EagerTensor/3/float, index:IndexMap/0/?, name:str/0/str · returned EagerTensor · level recorded 2026-09-24
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
tapas/models/tf_utils.py ran fingerprinted Apache-2.0 (permissive) · 44a49b752068dd08 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
get_answer_indexes tapas/utils/prediction_utils.py ran Apache-2.0 (permissive) · 2bdc76acdd4efd43 · report fixture: signature prediction:dict/0/?, cell_classification_threshold:float/0/float · returned list · level recorded 2026-09-24
get_correct_powerset tapas/utils/interpretation_utils.py ran Apache-2.0 (permissive) · 2f4d3cb79e069b0d · report fixture: signature indices:list/1/int, values:dict/0/?, is_correct_fn:callable/0/? · returned set · level recorded 2026-09-24
get_initializer in 32 papers tapas/models/modeling.py ran Apache-2.0 (permissive) · d05bac24655b6e92 · report fixture: signature initializer_range:float/0/float · returned TruncatedNormal · level recorded 2026-09-24
get_mean_cell_probs tapas/utils/prediction_utils.py ran Apache-2.0 (permissive) · 0d68ef2cc5138081 · report fixture: signature prediction:dict/0/? · returned dict · level recorded 2026-09-24
is_ordinal tapas/utils/number_utils.py ran Apache-2.0 (permissive) · cfe3053c233813ea · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-24
pack_inputs tapas/models/tf_utils.py ran Apache-2.0 (permissive) · 8c8db6c2cff0952b · report fixture: signature inputs:list/1/EagerTensor · returned tuple · level recorded 2026-09-24
range_index_map tapas/models/segmented_tensor.py ran Apache-2.0 (permissive) · 4617c8d5aef65a35 · report fixture: signature batch_shape:EagerTensor/1/int, num_segments:EagerTensor/0/int, name:str/0/str · returned IndexMap · level recorded 2026-09-24
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input
tapas/models/tf_utils.py ran Apache-2.0 (permissive) · c2414a1393c4800e · report fixture: signature features:SymbolicTensor/2/float · returned EagerTensor · level recorded 2026-09-24
tokenize_string tapas/utils/text_utils.py ran fingerprinted Apache-2.0 (permissive) · 84b82f831409eb64 · report fixture: signature x:str/0/str · returned list · level recorded 2026-09-25
wtq_normalize tapas/utils/text_utils.py ran fingerprinted Apache-2.0 (permissive) · a266b518abe797d8 · report fixture: signature x:str/0/str · returned str · level recorded 2026-09-24

Tasks

Question AnsweringSemantic ParsingTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Parsing SQA TAPAS-Large Accuracy 67.2 #2 of 2 Archive leaderboard report
Semantic Parsing WikiSQL TAPAS-Large (weak supervision) Denotation accuracy (test) 83.6 #5 of 5 Archive leaderboard report
Semantic Parsing WikiTableQuestions TAPAS-Large (pre-trained on SQA) Accuracy (Dev) / #20 of 22 Archive leaderboard report
Semantic Parsing WikiTableQuestions TAPAS-Large (pre-trained on SQA) Accuracy (Test) 48.8 #20 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

TAPAS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections