StruBERT: Structure-aware BERT for Table Search and Matching

TL;DR

StruBERT is a novel structure-aware BERT model that effectively combines textual and structural information of data tables, significantly improving table retrieval and similarity tasks.

Contribution

This paper introduces StruBERT, a new neural model that fuses textual and structural data for enhanced table understanding and retrieval.

Findings

Substantial improvements over state-of-the-art in retrieval metrics

Effective fusion of textual and structural information

Versatile application to multiple table-related tasks

Abstract

A large amount of information is stored in data tables. Users can search for data tables using a keyword-based query. A table is composed primarily of data values that are organized in rows and columns providing implicit structural information. A table is usually accompanied by secondary information such as the caption, page title, etc., that form the textual information. Understanding the connection between the textual and structural information is an important yet neglected aspect in table retrieval as previous methods treat each source of information independently. In addition, users can search for data tables that are similar to an existing table, and this setting can be seen as a content-based table retrieval. In this paper, we propose StruBERT, a structure-aware BERT model that fuses the textual and structural information of a data table to produce context-aware representations for both textual and tabular content of a data table. StruBERT features are integrated in a new end-to-end neural ranking model to solve three table-related downstream tasks: keyword- and content-based table retrieval, and table similarity. We evaluate our approach using three datasets, and we demonstrate substantial improvements in terms of retrieval and classification metrics over state-of-the-art methods.