Varish Mulwad

PhD, Computer Science (University of Maryland, Baltimore County) MS, Computer Science (University of Maryland, Baltimore County) BE, Computer Engineering (University of Mumbai)

Varish Mulwad is a Lead Scientist in the Artificial Intelligence technology domain at GE Research. His research focuses on extracting information from unstructured, semi-structured and structured sources to automatically populate knowledge graphs. He does this by leveraging techniques from areas such as the Semantic Web, natural language processing (NLP) and machine learning.

At GE Research, along with expanding the state of the art, Dr. Mulwad also focuses on developing solutions to improve industrial productivity. For example, he led the development of an AI agent to assist human IT agents in classifying IT tickets into categories, recommending possible resolutions for new problems and recommending experts that can assist in resolving complex issues. The AI agent, deployed in production and used by GE’s IT tech agents, led to significant productivity gains. In addition, he was part of a team that developed NLP algorithms for extracting concepts from medical documents and recommending relevant documents from a patient's history to radiologists. He further led the effort to transition these algorithms into GE Healthcare’s medical imaging software product. He is currently developing NLP algorithms for the extraction of scientific concepts and equations from text as part of DARPA’s Automating Scientific Knowledge Extraction (ASKE) program.

Dr. Mulwad obtained an MS (2010) and PhD (2015) in Computer Science from the University of Maryland, Baltimore County (UMBC). He has 15+ publications with 400+ citations and holds 3 patents with multiple pending patent applications.

What excites me at GE Research is the opportunity to work on problems from a diverse set of domains alongside some amazing people!

  1. 2016

    First version of the AI agent for IT tech agents deployed to production environment.
  2. NLP algorithms for concept extraction from medical documents and recommendation of relevant document from patient history to radiologists demoed at RSNA under the IRCC initiative.

    2017

Publications

  1. Cuddihy, P., McHugh, J., Williams, J.W., Mulwad, V. and Aggour, K., SemTK: A Semantics Toolkit for User-friendly SPARQL Generation and Semantic Data Management.
  2. Tari, L., Mulwad, V. and von Reden, A., 2016, June. Interactive online learning for clinical entity recognition. In Proceedings of the Workshop on Human-In-the-Loop Data Analytics (p. 8). ACM.
  3. Cuddihy, P., McHugh, J., Williams, J.W., Mulwad, V. and Aggour, K.S., 2017. SemTK: An Ontology-first, Open Source Semantic Toolkit for Managing and Querying Knowledge Graphs. arXiv preprint arXiv:1710.11531.
  4. McHugh, J., Cuddihy, P.E., Williams, J.W., Aggour, K.S., Kumar, V.S. and Mulwad, V., 2017, December. Integrated Access to Big Data Polystores through a Knowledge-driven Framework. In Big Data (Big Data), 2017 IEEE International Conference on (pp. 1494-1503). IEEE.

We're ready to partner with you. 

Contact Us