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


HYTREL: Hypergraph-enhanced Tabular Data Representation Learning

Language models pretrained on large collections of tabular data have dem...

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

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

TransTab: Learning Transferable Tabular Transformers Across Tables

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

Learning Better Representation for Tables by Self-Supervised Tasks

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

UniTabE: Pretraining a Unified Tabular Encoder for Heterogeneous Tabular Data

Recent advancements in Natural Language Processing (NLP) have witnessed ...

Table Retrieval May Not Necessitate Table-specific Model Design

Tables are an important form of structured data for both human and machi...

Topology preserving thinning for cell complexes

A topology preserving skeleton is a synthetic representation of an objec...

Please sign up or login with your details

Forgot password? Click here to reset