Papers › TABBIE: Pretrained Representations of Tabular Data

TABBIE: Pretrained Representations of Tabular Data

6 May 2021NAACL 2021 4arXiv:2105.02584archive 2025-07-28

Hiroshi Iida, Dung Thai, Varun Manjunatha, Mohit Iyyer

Existing work on tabular representation learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving paired tables and text (e.g., answering questions about tables), we show that it underperforms on tasks that operate over tables without any associated text (e.g., populating missing cells). We devise a simple pretraining objective (corrupt cell detection) that learns exclusively from tabular data and reaches the state-of-the-art on a suite of table based prediction tasks. Unlike competing approaches, our model (TABBIE) provides embeddings of all table substructures (cells, rows, and columns), and it also requires far less compute to train. A qualitative analysis of our model's learned cell, column, and row representations shows that it understands complex table semantics and numerical trends.

Paper PDF Conference PDF Code

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

Code

SFIG611/tabbie officialmentioned in papermentioned on GitHubpytorchMIT report

awslabs/hypergraph-tabular-lm mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cell Detection Column Type Annotation Representation Learning Table annotation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Column Type Annotation	VizNet-Sato-Full	TaBERT	Weighted-F1	97.2	#4 of 4	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

Introduced by this paper: TABBIE

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax TABBIE Weight Decay WordPiece

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