Beyond Context: Answering Deeper Questions by Combining Spark NLP and Graph Database Analytics

The first challenge of “ad hoc data analysis” is semantic, not technological. Data analytics users could be a patient, practitioner, administrator, or data scientist —the results don’t change based on the person asking the questions.

Lack of Interoperability between natural language and structured languages (SQL) leads to multiple interfaces, models, and views of the same data. Fortunately, the use of modern natural language processing (NLP) and graph modeling techniques minimizes such challenges.

TigerGraph, a distributed graph database, serves the purpose of semantic modeling, multi-sources integration, ad-hoc query analysis, compliance, and regulations.

Spark NLP for Healthcare – the most widely used, accurate, and scalable medical NLP library – provides linguistic, semantic, contextual, and personalized capabilities. This session describes an end-to-end solution that exceeds current BI platforms and delivers on connected analytics by exposing data patterns that combine conversational, predictive, and inference purposes.

For example, how do we go beyond “Who was the first Covid Patient?” to also answer “How will the city be impacted in the next 2 days?” Join us for a practical NLP solution that delivers state-of-the-art results with a quick implementation of Big Data in the healthcare domain.

About the speaker

Abhishek Mehta

Director Field Engineering at TigerGraph

Abhi runs the Sales Engineering team at TigerGraph and has worked with the majority of our customers in the Financial Services, Healthcare, and eCommerce domain. He has built his career around Enterprise Software, Graph Databases, Search Engines and holds Patents in Natural Language Processing spanning Conceptunary, Ontology Design, Language Pattern Recognition, and Conversion. Prior to TigerGraph, Abhi has worked at McKinsey, Bloomberg, Cisco & Dabizmo (NLP Startup) as Founder.

About the speaker

Christian Kasim Loan

Senior Data Scientist at John Snow Labs

Christian Kasim Loan is a Senior Data Scientist and Scala expert at John Snow Labs. He is a Computer Scientist with over a decade of experience in software and worked on various projects in Big Data, Data Science and DevOps using modern technologies such as Kubernetes, Docker, Spark, Kafka, Hadoop, and almost 20 programming languages to create modern cloud-agnostic AI solutions through his consulting company CKL-IT.

He has deep knowledge of Time-Series Graphs from his previous research in scalable and accurate traffic flow prediction and working on various Spatio-Temporal problems embedded in graphs at a Daimler lab.

Before his graph research, he worked on scalable meta machine learning, visual emotion extraction, and chatbots for various use cases at the Distributed Artificial Intelligence lab (DAI) in Berlin. His most recent work includes the NLU library, which democratizes 1000+ state-of-the-art NLP models in 200+ languages in just 1 line of code.