A Hybrid Approach and Unified Framework for Bibliographic Reference Extraction
Preprint
Abstract
Publications are an integral part in a scientific community. Bibliographic reference extraction from scientific publication is a challenging task due to diversity in referencing styles and document layout. Existing methods perform sufficiently on one dataset however, applying these solutions to a different dataset proves to be challenging. Therefore, a generic solution was anticipated which could overcome the limitations of the previous approaches. The contribution of this paper is three-fold. First, it presents a novel approach called DeepBiRD which is inspired by human visual perception and exploits layout features to identify individual references in a scientific publication. Second, we release a large dataset for image-based reference detection with 2401 scans containing 38863 references, all manually annotated for individual reference. Third, we present a unified and highly configurable end-to-end automatic bibliographic reference extraction framework called BRExSys which employs DeepBiRD along with state-of-the-art text-based models to detect and visualize references from a bibliographic document. Our proposed approach pre-processes the images in which a hybrid representation is obtained by processing the given image using different computer vision techniques. Then, it performs layout driven reference detection using Mask R-CNN on a given scientific publication. DeepBiRD was evaluated on two different datasets to demonstrate the generalization of this approach. The proposed system achieved an AP50 of 98.56% on our dataset. DeepBiRD significantly outperformed the current state-of-the-art approach on their dataset. Therefore, suggesting that DeepBiRD is significantly superior in performance, generalized, and independent of any domain or referencing style.Keywords
All Related Versions
- Version 1, 2019-12-16, ArXiv
- Version 2, 2020-10-08, ArXiv
- Published version: IEEE Access, 8, 217231.
This publication has 8 references indexed in Scilit:
- FLAG-PDFe: Features Oriented Metadata Extraction Framework for Scientific PublicationsIEEE Access, 2020
- Linked Open Citation Database2018
- Neural ParsCit: a deep learning-based reference string parserInternational Journal on Digital Libraries, 2018
- The journal coverage of Web of Science and Scopus: a comparative analysisScientometrics, 2015
- CERMINE: automatic extraction of structured metadata from scientific literatureInternational Journal on Document Analysis and Recognition (IJDAR), 2015
- Locating and parsing bibliographic references in HTML medical articlesInternational Journal on Document Analysis and Recognition (IJDAR), 2010
- BibPro: A Citation Parser Based on Sequence Alignment Techniques2008
- Long Short-Term MemoryNeural Computation, 1997