Metric-Type Identification for Multi-Level Header Numerical Tables in Scientific Papers

TL;DR

This paper introduces a new task of metric-type identification in multi-level header numerical tables from scientific papers, along with a dataset and neural models that improve understanding of table metrics.

Contribution

It presents the first dataset and neural models for metric-type identification in multi-level header tables, combining classification and generation techniques.

Findings

Joint models effectively identify metric-types within and outside headers.

BERT-based models outperform pointer-generator models.

The approach enhances automatic table understanding in scientific literature.

Abstract

Numerical tables are widely used to present experimental results in scientific papers. For table understanding, a metric-type is essential to discriminate numbers in the tables. We introduce a new information extraction task, metric-type identification from multi-level header numerical tables, and provide a dataset extracted from scientific papers consisting of header tables, captions, and metric-types. We then propose two joint-learning neural classification and generation schemes featuring pointer-generator-based and BERT-based models. Our results show that the joint models can handle both in-header and out-of-header metric-type identification problems.