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.