Research

My current research interests are into extracting knowledge like events, entities and factual legitimacy from unstructured text. I am also interested in using external factual knowledge and constraints (entity types/domain-knowledge/language/sentiment) in improving downstream natural language processing (NLP) application like language modeling (LM), question answering (QA), summarization (SM).

My work at the Department of Computer Science and Electrical Engineering at the University of Maryland Baltimore County (UMBC) was at the intersection information extraction and representation learning. My work specifically focused on learning information extraction tasks like knowledge graph embedding, entity typing with language modeling principles. The work provides broader understanding in using the knowledge from these tasks to improve generative capacity of downstream NLP tasks like LM, QA etc.

Publications

Published Papers

• Rajat Patel. (2023). InterosML @ Causal News Corpus 2023: Understanding Causal Relationships: Supervised Contrastive Learning for Event Classification
• Rajat Patel , Francis Ferraro. (2020). On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling
• Rajat Patel. (2020). Jointly Learning Knowledge Graph Embeddings, Fine Grain Entity Types and Language Models (Master thesis)

  Read More