A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries

Abstract

Information extraction can support novel and effective access paths for digital libraries. Nevertheless, designing reliable extraction workflows can be cost-intensive in practice. On the one hand, suitable extraction methods rely on domain-specific training data. On the other hand, unsupervised and open extraction methods usually produce not-canonicalized extraction results. This paper tackles the question how digital libraries can handle such extractions and if their quality is sufficient in practice. We focus on unsupervised extraction workflows by analyzing them in case studies in the domains of encyclopedias (Wikipedia), pharmacy and political sciences. We report on opportunities and limitations. Finally we discuss best practices for unsupervised extraction workflows.

arXiv commentAccepted at JCDL2022, 11 pages, 1 figure

References in corpus (4)

• Efficient Estimation of Word Representations in Vector Space
• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
• CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information

Cited by in corpus (1)

• A Library Perspective on Supervised Text Processing in Digital Libraries: An Investigation in the Biomedical Domain