Populating and leveraging semantic knowledge graphs to supercharge search

Chris Morley • Location: Theater 7 • Back to Haystack 2023

Detecting, acquiring and organizing knowledge from text using automated NLP methods enables us to search for “things”, rather than merely “strings.” We will show how to recognize conceptual entities and relationships from documents written in English. We then insert these objects into a semantic knowledge graph. Doing so unlocks new options. We may use this system offline to help build synonym lists or help us enrich documents. Using it online, we may do query expansion or relaxation, tune boosts, choose an optimal query handler, or perform user intent recognition. We will show that it is useful to load additional text to teach the system about the existence of additional things and how they relate to common concepts in our domain. Before, obscure long-tail queries had no chance of matching our domain focused corpus; now, we reduce the frequency of zero result searches, capturing new business. Subject matter experts may explore the graph and make additions and corrections.

Download the Slides

Chris Morley

OpenSource Connections LLC

Chris Morley joined OpenSource Connections in April 2022 after working for several Fortune 500 companies and several other companies in a variety of domains using Lucene-based search technologies like Solr and Elasticsearch for over a decade and has been a professional software developer for more than two decades and a programmer for more than three decades. He is a creative person and a deep thinker and is fullstack architect and computer scientist with broad skills in many programming languages, operating systems, database systems and cloud platforms. His central interest is using distributed data systems to build next generation smart web services that are lightning fast and solidly robust. He first became interested in search technologies due to the data performance characteristics that they showcase, and has since put them to use in e-commerce and GIS applications. As a result of this work, he has become interested in expanding his knowledge and capabilities with regard to data pipelines and message queues, data science and artificial intelligence, and linguistics. Complex systems which feature multiple actors that interact, self-organize and display emergent attributes and capabilities are absolutely fascinating to Chris, so things like computational neuroscience, computer vision, the philosophy of mind, deep learning, data visualizations and animated data simulations are all very exciting areas of interest, at least for recreational reading. He hopes that humanity, equipped with the Internet and the latest advances in artificial intelligence, will finally figure out exactly how consciousness operates and open source its schematics!