SAPIENT Automation - Web Annotation Tool
Introduction
The goal of the SAPIENT Automation project is to evaluate the outcomes of the soon-to-be-finished JISC funded project ART, to assess the added benefit from annotating core scientific concepts (e.g. 'Goal', 'Experiment', 'Method', 'Result', 'Conclusion', etc.) in research papers. The ART project produced a Corpus of 200 papers (~ 4 million words) from Physical Chemistry and Biochemistry annotated with such concepts, as well as a web annotation tool SAPIENT, which allowed 16 experts to manually annotate the papers.
Aims and objectives
- Evaluate the sustainability of the CISP meta-data by training existing machine learning methods on the ART Corpus and comparing the generated scientific content meta-data against the manual annotations
- Evaluate the usefulness of the meta-data obtained in this way by using it to generate structured digital abstracts