Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations

TR Number
Journal Title
Journal ISSN
Volume Title

Electronic Theses and Dissertations (ETDs) contain domain knowledge that can be used for many digital library tasks, such as analyzing citation networks and predicting research trends. Automatic metadata extraction is important to build scalable digital library search engines. Most existing methods are designed for born-digital documents such as GROBID, CERMINE, and ParsCit, so they often fail to extract metadata from scanned documents such as for ETDs. Traditional sequence tagging methods mainly rely on text-based features. In this paper, we propose a conditional random field (CRF) model that combines text-based and visual features. To verify the robustness of our model, we extended an existing corpus and created a new ground truth corpus consisting of 500 ETD cover pages with human validated metadata. Our experiments show that CRF with visual features outperformed both a heuristic baseline and a CRF model with only text-based features. The proposed model achieved 81.3%-96% F1 measure on seven metadata fields. The data and source code are publicly available on Google Drive1 and a GitHub repository2.

Science & Technology, Technology, Computer Science, Information Systems, Computer Science, Interdisciplinary Applications, Computer Science, Theory & Methods, Information Science & Library Science, Computer Science, Digital Libraries, Optical Character Recognition, Text Mining, Metadata Extraction, CRF, BiLSTM, 31 Biological Sciences, 3102 Bioinformatics and Computational Biology, 46 Information and Computing Sciences, 4605 Data Management and Data Science, 4610 Library and Information Studies