ACCIO: Table Understanding Enhanced via Contrastive Learning with Aggregations

TL;DR

ACCIO introduces a novel contrastive learning approach that enhances table understanding by comparing tables with their summaries, achieving high accuracy in column type annotation and advancing table comprehension techniques.

Contribution

This work is the first to utilize pairs of tables for embedding, significantly improving table understanding through contrastive learning with aggregations.

Findings

Achieves a macro F1 score of 91.1 in column type annotation.

First to leverage table pairs for embedding in table understanding.

Demonstrates the effectiveness of contrastive learning with aggregations.

Abstract

The attention to table understanding using recent natural language models has been growing. However, most related works tend to focus on learning the structure of the table directly. Just as humans improve their understanding of sentences by comparing them, they can also enhance their understanding by comparing tables. With this idea, in this paper, we introduce ACCIO, tAble understanding enhanCed via Contrastive learnIng with aggregatiOns, a novel approach to enhancing table understanding by contrasting original tables with their pivot summaries through contrastive learning. ACCIO trains an encoder to bring these table pairs closer together. Through validation via column type annotation, ACCIO achieves competitive performance with a macro F1 score of 91.1 compared to state-of-the-art methods. This work represents the first attempt to utilize pairs of tables for table embedding, promising significant advancements in table comprehension. Our code is available at https://github.com/whnhch/ACCIO/.