Webinar: Mirror, Mirror, on the Wall: What Country Will Rule Them All?
Accurate Geopolitical Forecasting with NLP
Superforecaster Carolyn Meinel and her team leapt from 27th place to 2nd place in three months during IARPA’s 11-month long Geopolitical Forecasting Challenge 2. This improvement came in large part by adding sophisticated natural language processing tools to triage data. Learn how the team used semantic search and entity extraction to surface useful, accurate data from massive, noisy datasets — sometimes containing misleading information — to enable the team’s human forecasters to predict answers to 305 geopolitical questions covering a staggering range of topics.
Carolyn will present specific examples of how cross-lingual semantic search delivered the relevant paragraphs of documents, from which she could forecast answers that could not normally be discovered from keyword searches or with less than a roomful of subject matter experts.
May 20, 2020 at 12:00 pm ET
9:00 am: PT
12:00 am: ET
5:00 pm: London
7:00 pm: Tel Aviv
Senior Research Fellow
Institute for Strategic and Innovative Technologies
Carolyn Meinel is Chief Technology officer of the Institute for Strategic and Innovative Technologies, https://isistaustin.org. Since 2014, she has focused upon the science and practice of geopolitical forecasting. She participated in the iterative design and deployment of the Team KaDSci system in the 2019 Geopolitical Forecasting Challenge conducted by Intelligence Advanced Projects Agency (IARPA). Currently she is participating in IARPA’s Forecasting Counterfactuals in Uncontrolled Settings (FOCUS) program. https://www.iarpa.gov/index.php/research-programs/focus. Her article “Code Red for the Web” (Scientific American, Oct. 2001) https://www.scientificamerican.com/article/code-red-worm-assault-on/ was reprinted in the book, Best American Science Writing, 2002 and the college textbook Computers in Society. Her refereed publications include "For Love of a Gun," history, technologies of electromagnetic guns, IEEE Spectrum, July, 2007; "Cybercrime Treaty Could Chill Research," IEEE Security and Privacy, July/Aug. 2004, pp. 28-32; C.P. Meinel, L.M. Gutheinz, A.J. Toepfer, R.Vandenberg, and R. Weitz, "Remote Resource Mapping of Solar System Bodies," Engineering, Construction and Operations in Space, Proceedings of the Space 90 Conference, ASCE, Johnson, S.W. and Wetzel, J.P., eds., April 22-26, 1990; Fair, H.D., Coose, P., Meinel, C.P. and Tidman, D.A. "Electromagnetic Earth-to-Space Launch," IEEE Transactions on Magnetics, January 1989.
Federal Solutions Engineer
Eugene has 20 years of experience in software engineering, mainly in several offices within the Intelligence Community. He has been part of multiple applied research and development organizations, focusing on advancing text analytics through various human language technologies (HLT), such as Latent Semantic Indexing (LSI), entity identification, and machine translation. Growing up, he learned to program at an early age, lectured programming classes, tutored students, and led multimedia productions. Eugene obtained a B.S. in Computer Science and minor in Political Science at Virginia Polytechnic Institute and State University.