Hitarth Narvala

Sir Alwyn Williams Building, Room 502
University of Glasgow
Glasgow G12 8QQ 

Email: h.narvala.1@research.gla.ac.uk

Research title: Learning from User Actions through the Identification of Latent Relationships in Sensitive Documents

Research Summary

I am a PhD student in the Information Retrieval Group, School of Computing Science. My Supervisors are Professor Iadh Ounis and Dr. Graham McDonald. My research is focussed on technology-assisted sensitivity review that is performed to identify and protect sensitive information such as personal or confidential information in large collections of digital documents. The research specifically aims to augment information retrieval methods with effective machine learning techniques, for example, reinforcement learning to continuously learn from the actions and interactions of the sensitivity reviewers to classify sensitive information more accurately and improvise the discovery of latent relations between documents, entities and events.

Research Interests:

  • Sensitivity Classification
  • Reinforcement Learning for NLP
  • Technology Assisted Review
  • Graph Search

Publications

  • Receptor: A Platform for Exploring Latent Relations in Sensitive Documents
    Hitarth Narvala, Graham McDonald and Iadh Ounis. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval 2020, (SIGIR 2020) (PDF)