Join us at Fidelity's downtown Boston office to learn about new developments in the Apache Lucene and Solr that help you get the most out of your search. We welcome all Solr/Lucene developers, devops and data engineers, machine learning engineers, DBAs, product managers and users to come share their stories, questions, and curiosity.
Talk 1: "Thought Vectors and Knowledge Graphs in AI-Powered Search"
While traditional keyword search is still useful, pure text-based keyword matching is quickly becoming obsolete; today, it is a necessary but not sufficient tool for delivering relevant results and intelligent search experiences.
In this talk, we'll cover some of the emerging trends in AI-powered search, including the use of thought vectors (multi-level vector embeddings) and semantic knowledge graphs to contextually interpret and conceptualize queries. We'll walk through some live query interpretation demos to demonstrate the power that can be delivered through these semantic search techniques leveraging auto-generated knowledge graphs learned from your content and user interactions.
* Trey Grainger, Lucidworks' Chief Algorithm Officer, drives vision and practical application of intelligent data science algorithms to power relevant search experiences for hundreds of the worlds biggest and brightest companies. He is author of the books "AI-Powered Search" and "Solr in Action", plus more than a dozen additional books, journal articles, and research publications covering industry-leading approaches to semantic search, recommendation systems, and intelligent information retrieval systems.
Talk 2: Semantic Search Across Languages with Word Embeddings
How can we search data for concepts we have never seen before? Word embeddings allow us to go beyond the exact text in documents and store them in a semantic search space. This talk will begin with a brief overview of what word embeddings are and how they are created, followed by a discussion of how they can be extended into a multilingual semantic space, allowing users to search for ideas across languages.
* Gil Irizarry, Basis Technology's VP, Engineering, who leads the text analytics team that builds plugins for Lucene and Solr boost precision and recall in multilingual search as well as fuzzy name matching to overcome spelling variation and cross-lingual headaches.
* Philip Blair, Senior Research Engineer on Basis Technology’s R&D team. He investigates practical applications of deep learning technologies for use in text analytics. Philip also leads Basis Technology’s machine learning infrastructure team, focused on deploying cutting-edge algorithms into the field.