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

arXiv: https://arxiv.org/abs/2107.00516 · HTML: https://mlsanity.com/paper/2107.00516/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 16 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 2 of 2)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Keyphrase Extraction using Sequential Labeling](https://mlsanity.com/paper/1608.00329/) (2016)

## Built on by (most cited first, 3 of 3)

- [The Impact of Modern AI in Metadata Management](https://mlsanity.com/paper/2501.16605/) (2025)
- [MetaEnhance: Metadata Quality Improvement for Electronic Theses and Dissertations of University Libraries](https://mlsanity.com/paper/2303.17661/) (2023)
- [ETDPC: A Multimodality Framework for Classifying Pages in Electronic Theses and Dissertations](https://mlsanity.com/paper/2311.04262/) (2023)

## Abstract (arXiv)

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, 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 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 Drive (https://tinyurl.com/y8kxzwrp) and a GitHub repository (https://github.com/lamps-lab/ETDMiner/tree/master/etd_crf), respectively.