Companies in the financial sector (banks, insurance companies, auditors, etc.) are under increased pressure due to regulatory demand for improved transparency, accountability, and security, which requires sophisticated information management capabilities. As a large part of their information consists of text data like email, memos, and phone transcripts or business documents like contracts, companies are forced to constantly increase their headcount to keep up with the ever-growing workload. These jobs tend to be problematic as they require a high degree of skill to perform very repetitive tasks. As such, automating them would have a huge cost-saving potential.
In order to automate and power use cases like compliance monitoring, KYC, or contract intelligence, computers need the ability to understand the meaning of text—a task at the heart of artificial intelligence. Current state-of-the-art approaches to infer the meaning of text mostly rely on statistically built language models. Statistical models have to be highly simplified for computational reasons, and due to the lack of semantic grounding (referential instead of direct representation), a fair amount of noise is introduced into the processing pipeline. This leads to phenomena like false positives or the need for massive amounts of training data, both of which are often prohibitive in the business context.
Francisco Webber explains how Cortical.io’s semantic folding, a neuroscience-based approach to natural language understanding, helps solve many uses cases efficiently and elegantly.
Francisco Webber is co-founder and CEO of Cortical.io, a company that develops natural language understanding solutions for analyzing the big text data of large enterprises. The solutions are based on the actual meaning, rather than on statistical occurrences, of text.
Francisco’s interest in information technology developed during his medical studies, when he was involved in medical data processing. Over two decades he explored search engine technologies and documentation systems in different contexts but became increasingly frustrated with the limitations of statistical methods.
Francisco recognized that the brain was the only high-performing system when it came to natural language understanding. While closely following developments in neuroscience, he formulated his theory of Semantic Folding, which models how the brain processes language data. In 2011, he co-founded Cortical.io to apply the principles of cerebral processing to machine learning and text processing and solve real-world use cases related to big data.
Comments on this page are now closed.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org