Relation Extraction from Tables using Artificially Generated Metadata

TL;DR

This paper introduces methods to generate artificial metadata for synthetic tables from Knowledge Graphs, enhancing relation extraction accuracy by 9-45% F1 score using a BERT-based model.

Contribution

It proposes techniques to create artificial metadata for synthetic tables, improving relation extraction performance from such tables.

Findings

Artificial metadata improves RE accuracy significantly.

BERT-based model benefits from combined metadata and table content.

Empirical results show 9-45% F1 score improvement.

Abstract

Relation Extraction (RE) from tables is the task of identifying relations between pairs of columns of a table. Generally, RE models for this task require labelled tables for training. These labelled tables can also be generated artificially from a Knowledge Graph (KG), which makes the cost to acquire them much lower in comparison to manual annotations. However, unlike real tables, these synthetic tables lack associated metadata, such as, column-headers, captions, etc; this is because synthetic tables are created out of KGs that do not store such metadata. Meanwhile, previous works have shown that metadata is important for accurate RE from tables. To address this issue, we propose methods to artificially create some of this metadata for synthetic tables. Afterward, we experiment with a BERT-based model, in line with recently published works, that takes as input a combination of proposed artificial metadata and table content. Our empirical results show that this leads to an improvement of 9\%-45\% in F1 score, in absolute terms, over 2 tabular datasets.