CEVOpen Blog Ideas

Thoughts on the blog and key messages:

• Simon
• PMR

Present Scenario:

Climate change, pandemics, and so on. How to tackle these challenges as humanity progresses? With the advent of technology and automation, we ought to make the best use of it. But are we really doing it? How can automation and mining text data help in contributing to solve global challenges?

Defining the problem

You have read a newspaper article about climate change, and you’d like to dig deeper. You open up a paper filled with jargon and terms you don’t understand. How would you make sense of it?

Or if you are a researcher and would like to know more about something that is out of your domain expertise. With research articles mainly aimed at communicating knowledge only with the experts of the area, how can penetrate through these barriers? What makes the problem worse is the plethora of scientific papers that are out there.

One other grave problem is that publishers of scientific articles control what you see. This is a problem whose solutions lie beyond just creating tools. The involvement of communities plays an essential role here in changing the current model of publishing.

Explain the manual process of going through a paper You can then correlate to how we can automate some of these steps.

Potential solution

There are several ways of tackling such problems. There are various tools that aim at doing exactly that. Scholia, openknowledgemap, and so on. We would like to concentrate on the tools we are developing.

Text-Mining and Wikidata integration - one of the solutions At CEVOpen, we are building tools that automate some parts of the workflow. The main focus of pyami is integration with Wikidata. Wikidata, for those who aren’t aware, is a sister project of Wikipedia. You could think of it like a … . Our tools, at the very least, can go through scientific papers and annotate them with the terms we provide. We call the collection of terms -> ami dictionaries. These dictionaries are customizable, and you can create your own ones. Some include country, organization, plant genus, and so on. You can find the full list of available dictionaries here.

What’s interesting with integrating with Wikidata is that we can get simple definitions instantaneously. Wikidata like Wikipedia also stores information in multiple languages. This allows non-native English speakers to look up definitions for terms in their native language.

If all of this seems a little abstract, we’ve got a case study for you to better appreciate the technology.

Case Study: Ethics Statement, Invasive Species or Activity.

An example for putting the technology to use in a targeted fashion.

…

Ami is still developing, and would very much appreciate any inputs from the early adopters and user community. As we have seen with the pandemic, openly sharing knowledge is key to solve global challenges like climate change, and so on.