Shweata N. Hegde
I am an aspiring science communicator and a science education enthusiast with a love for open science. I am currently a third-year undergrad studying life sciences and education at the Regional Institute of Education, Mysuru. I've been an intern at CEVOpen (and openVirus) for about a year now.
At India's National Institute for Plant Genome Research we are developing Wikidata as a central tool to mine the plant chemistry literature. As part of our regular student intern program, especially during the pandemic, students from all over India join us in short internships to do research in a collaborative Open Notebook-based project (CEVOpen). We create mini-ontologies from Wikidata as search and annotation tools, which then link back to Wikimedia resources.
Coming from a non-technical background, the interns:
- have learnt how to use Wikidata
- are creating dictionaries from scoping the literature
- are using Text Data-Mining (TDM) tools to make multidisciplinary inferences.
In this short presentation, you will hear each of them speak about various aspects of dictionary creation and TDM, challenges, learnings, their experience and demo some CEVOpen tools.
Because Wikidata supports many languages we have developed our code to support discovery and annotation in non-English languages.