Building & Querying Enterprise Knowledge Bases: From Declarative Languages to GenAI

Name: Building & Querying Enterprise Knowledge Bases: From Declarative Languages to GenAI
Start: 2024-11-28T14:00:00+02:00
End: 2024-11-28T15:00:00+02:00
Location: Universitatea POLITEHNICA din București

Schedule

Thu Nov 28 2024 at 02:00 pm to 03:00 pm

UTC+02:00

Location

Universitatea POLITEHNICA din București | Bucharest, BU

📢 Join us for an insightful talk by Shiv Vaithyanathan, VP of Platform Engineering at Adobe DX, at the Polytechnic University of Bucharest! Shiv will explore the journey of building and querying enterprise knowledge bases, from declarative languages to Generative AI.
🗓 Date: 28 November
⏰Time: 14:00 - 15:00 Speech and Q&A
📍 Location: Polytechnic University of Bucharest, Precis Building, room PR001
Access: Based only on registration: https://forms.office.com/r/peQzNM91MN
🎓 Students and professors are invited to attend—don’t miss this opportunity to learn from an industry expert!
📢 Join us for an insightful talk by Shiv Vaithyanathan, VP of Platform Engineering at Adobe DX, at the Polytechnic University of Bucharest! Shiv will explore the journey of building and querying enterprise knowledge bases, from declarative languages to Generative AI.
Bio: Shivakumar (Shiv) Vaithyanathan is VP of Platform Engineering in Adobe DX responsible for Data & AI. Prior to that he was an IBM Fellow – one of 331 in the history of IBM. Shiv has more than 50 published papers and 40 patents in the areas of NLP, databases, and machine learning. Shiv has been an invited speaker at multiple universities around the world and keynoted at top database and information retrieval conferences. Shiv is a recipient of the inaugural “Test-of-Time” award from the Association of Computational Linguistics (ACL) in 2018.
Abstract: Building & Querying Enterprise Knowledge Bases: From Declarative Languages to GenAI
Over the last 25 years -- search, knowledge graph and even large language model innovations have been adopted by consumers much before enterprises. The delay in adoption of such technologies in enterprises is largely due to two factors. First, enterprise knowledge bases vary widely based on industry verticals and even within an industry vertical by organization-specific terminology and vocabulary. Second, querying such knowledge bases needs to account for very low-tolerance enterprise users have for mistakes and hallucination.
In this talk I will describe tools to build, maintain and query such knowledge bases and the evolution of these tools over two decades. Specifically, the talk will focus on enterprise systems I have been involved in building, ranging from declarative information extraction / entity resolution & programmable search to opinionated chain-of-thought reasoning using large language models and entity linking. I will explain these systems using examples from enterprise search, legal, financial and customer experience applications.