Steven Gustafson | Connecting The Dots With Knowledge & Data
KGC 2021
•
16m
Knowledge graphs provide a way for us to capture and relate information into a representation that can mimic expert knowledge. One type of expert knowledge that has proven to be particularly useful in industry is reasoning by analogy, or using a replacement problem and solution pair to think about the solution to a new problem. At opposite ends of the ‘representation spectrum’ are logic systems, which can easily become overly constrained and complex, and statistical approaches, which can be easily influenced by nonsensical data. In this talk, I describe challenges and successes I’ve seen using analogical reasoning and how a knowledge graph approach combined with statistics and data can overcome deficiencies in both methods. To illustrate the case, I’ll demonstrate how our financial decision support application leverages analogical reasoning in several places to answer challenging questions when evaluating organizations.
Up Next in KGC 2021
-
Mark Grover | From Discovering To Tru...
Over a third of analyst time is spent in understanding what data exists, can it be trusted and how to use it. Countless Data Engineering time is spent in answering the same questions about data - what does that column mean, how does it get populated, how often does it update and if there’s any in...
-
Martynas Jusevicius | Data-centric Tr...
One of the key pieces of global infrastructure today is the web yet it continues to be developed using legacy technologies dating back to the 1960s. A result of using outdated technology in turn has created several major problems. First, relational data models are a primary contributor to the dat...
-
Alex Kalinowski | Structured To Unstr...
Identification of entities and the relations between them is a difficult task for traditional pattern-based matching or machine learning approaches; these techniques rapidly overfit training datasets and struggle to transfer to other contexts or domains. Utilizing outside knowledge, such as facts...
