KM World Text Analytics Forum
Nov 07 - 09, 2017
Basis Technology’s Senior VP, U.S. Public Sector, Christopher Biow will be speaking at this event on 11/9 from 3-3:45PM.
- Session Topic: Maximizing analytic value from multi-language text feeds
- Session Title: From Petabytes Down To Tweets: Analytic Value from Multi-Language Text
The universe of text analytics is largely constrained to the output of the entire human race. While this can and does result in huge, petabyte-scale problems, that human limitation nonetheless provides an upper bound on the size of our problems, in a way that falls well within the storage and computational limits of modern, distributed systems. Moreover, these systems can focus down from that petascale universe to a specific span of a few words that express human assertions or sentiment about a specific, named entity. We can then resolve that reference to a real-world identity, and specific words about it to robust semantic expressions. Technologies for this scalability, computational distribution, deep learning, resolution, and semantic expression are all new within the last ten years, and their combination is revolutionary. Key to putting all of this together is that the text analytics are performed in the native language of the original text, prior to the inevitable loss of fidelity in machine or human translation. Join us as we explore examples based on actual government and commercial use for purposes including counterterrorism, Knowing Your Customer, border security, disease tracking, and detection and countering fake news and conspiracy theories.