Session 1: 8:30am-9:45am EST

Corpus creation from open access repositories and their analysis with semantic tools presented by Ms. Udita Agarwal, Ph.D. student, National Institute of Plant Genome Research (NIPGR) and Dr. Renu Kumari, Program Manager #semanticClimate and Ms. Shaik Zainab, Anurag University, Hyderabad. The session will provide an introduction to corpus creation and pygetpapers for literature review. Links to the recording will be available after the session.

They will be showing their complete READER-oriented toolkit. This takes OA material (both academic articles and more generally Open material such as the UN IPCC reports) and automatically turns it into semantic form (no AI contamination at this stage). There are several components, all Open, and managed by Renu, and largely automatic (i.e. their default use can scope a query in the time it takes to download material):

corpus builder
semantic encyclopedia
search
annotation
knowledge graphs
Jupyter notebooks for demonstration and learning

This is highly flexible (written in Python) but designed for use by those without technical knowledge (other than having Python on the machine).