Annotating Columns with Pre-trained Language Models

TL;DR

This paper introduces Doduo, a multi-task learning framework based on pre-trained language models, for annotating table columns by predicting types and relationships using only table data, achieving state-of-the-art results.

Contribution

The paper presents Doduo, a novel multi-task learning approach that leverages pre-trained language models to improve column annotation accuracy using minimal input tokens.

Findings

Doduo achieves up to 4.0% and 11.9% improvements on benchmark tasks.

It outperforms previous methods with only 8 tokens per column.

The approach is effective on real-world data science problems.

Abstract

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results show that Doduo establishes new state-of-the-art performance on two benchmarks for the column type prediction and column relation prediction tasks with up to 4.0% and 11.9% improvements, respectively. We report that Doduo can already outperform the previous state-of-the-art performance with a minimal number of tokens, only 8 tokens per column. We release a toolbox (https://github.com/megagonlabs/doduo) and confirm the effectiveness of Doduo on a real-world data science problem through a case study.