Jill Watson: A Suite of Online Learning Tools

From Left to Right: Ida Camacho, Qiaosi Wang, Rohit A Mujumdar, Ashok Goel, Eric Gregori, Varsha Achar

With the advent of Georgia Tech’s OMSCS (a massive online course to earn a Masters in CS), thousands of people around the world have been enrolling to learn. An increase in learners implied more questions being asked on class discussion forums. With a limited number of instructors per course, answering questions became increasingly difficult. This is when Jill Watson was conceived.

Jill Watson is a Virtual Teaching Assistant, that can answer questions about a course syllabus, when deployed on online communication forums like Piazza or Slack. 

What initially began as a question answering agent for course syllabi, Jill Watson is gradually permeating into other domains. Jill Watson can now answer questions about VERA‘s instructional manual.

Watch the video below to learn more about Jill Watson!

Hiring a Research Engineer

Help us develop AI to address ecological and environmental sustainability!

Georgia Tech’s Design & Intelligence Laboratory (http://dilab.gatech.edu/) seeks to hire a research engineer for its new NSF sponsored project on “Using Big Data for Environmental Sustainability: Big Data + AI Technology = Accessible, Usable, Useful Knowledge!”. A Spoke initiative of the NSF South Big Data Hub (http://www.southbdhub.org/),  this multi-university, interdisciplinary effort also engages Smithsonian Institution, IBM, and several other universities. Thus, the research engineer will work in an intellectually dynamic environment on a project with significant potential for real-world impact.

Project Description: Scientists need access to data on biodiversity for modeling ecological phenomena. Smithsonian Institution’s Encyclopedia of Life (EOL) is the world’s largest database of biological species and other biodiversity information. This project seeks to make EOL and related biodiversity data sources accessible, usable, and useful, by integrating extant artificial intelligence tools for information extraction, modeling and simulation, and question answering:

  • MILA-S: helps construct conceptual models of ecological phenomena and automatically spawns simulation models; uses MILA-S with EOL TraitBank to generate and test explanatory hypotheses as well as make predictions about ecosystems,
  • Cognopsi: semantically annotates documents in EOL by using controlled vocabularies for specific domains within ecological and environmental science, and
  • Watson+: adds semantic processing to IBM’s Watson system to act as a virtual research assistant; trains Watson+ to answer questions about biological species using EOL.

Position Description: The research engineer will help integrate the above technologies into one system for enabling citizen scientists to rapidly build conceptual and simulation models of ecological phenomena. Thus, the position will require significant experience and skills in building interactive software systems, as well as an ability to work in a large team on an interdisciplinary project. The ideal candidate would have a B.S. degree in computing with a several years of experience in software development, or a M.S. in computing and a few years of experience, or a Ph.D. in computing. The position is located in the Atlanta. Remuneration is competitive.

Contact: For more information, please contact Professor Ashok Goel at goel@cc.gatech.edu.

Errol

For aspiring start-up entrepreneurs, developing their Business Model Canvas (BMC) well is key to their future success. Errol is an interactive agent that aims to play the role of a teacher who can provide feedback on users’ BMCs. Using some heuristics and applying these through the methods of lexical and semantic analysis, Errol poses questions to users based on their BMCs. Users can then think about the answers to these questions and update their BMCs accordingly. And on an even more general scale, we can say that Errol may be a way to develop theories on how humans make errors and what we can do to fix those.