A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries
This work addresses the problem of reducing costs and improving access in digital libraries, but it is incremental as it focuses on analyzing existing methods rather than introducing new ones.
The paper tackled the challenge of designing cost-effective information extraction workflows for digital libraries by evaluating unsupervised methods across domains like Wikipedia, pharmacy, and political sciences, reporting on their practical quality and limitations.
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.