LAME: Layout Aware Metadata Extraction Approach for Research Articles

TL;DR

This paper introduces LAME, a layout-aware framework for extracting metadata from diverse research article layouts, utilizing automatic layout analysis, a large training set, and Layout-MetaBERT, achieving high accuracy on unseen formats.

Contribution

The paper presents a novel layout-aware metadata extraction framework with an automatic layout analysis, a large training dataset, and a specialized BERT model for diverse journal layouts.

Findings

Achieved 93.27% Macro-F1 in metadata extraction on unseen journal layouts.

Demonstrated robustness of Layout-MetaBERT across diverse layout formats.

Constructed a large, automatically extracted training dataset for metadata extraction.

Abstract

The volume of academic literature, such as academic conference papers and journals, has increased rapidly worldwide, and research on metadata extraction is ongoing. However, high-performing metadata extraction is still challenging due to diverse layout formats according to journal publishers. To accommodate the diversity of the layouts of academic journals, we propose a novel LAyout-aware Metadata Extraction (LAME) framework equipped with the three characteristics (e.g., design of an automatic layout analysis, construction of a large meta-data training set, and construction of Layout-MetaBERT). We designed an automatic layout analysis using PDFMiner. Based on the layout analysis, a large volume of metadata-separated training data, including the title, abstract, author name, author affiliated organization, and keywords, were automatically extracted. Moreover, we constructed Layout-MetaBERT to extract the metadata from academic journals with varying layout formats. The experimental results with Layout-MetaBERT exhibited robust performance (Macro-F1, 93.27%) in metadata extraction for unseen journals with different layout formats.