Log In Sign Up

TABBIE: Pretrained Representations of Tabular Data

by   Hiroshi Iida, et al.

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.


page 1

page 2

page 3

page 4


TransTab: Learning Transferable Tabular Transformers Across Tables

Tabular data (or tables) are the most widely used data format in machine...

FORTAP: Using Formulae for Numerical-Reasoning-Aware Table Pretraining

Tables store rich numerical data, but numerical reasoning over tables is...

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

Recent years have witnessed the burgeoning of pretrained language models...

OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering

The information in tables can be an important complement to text, making...

Learning Better Representation for Tables by Self-Supervised Tasks

Table-to-text generation aims at automatically generating natural text t...

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Physical measurements constitute a large portion of numbers in academic ...

StreamTable: An Area Proportional Visualization for Tables with Flowing Streams

Let M be an r× c table with each cell weighted by a nonzero positive num...