I am a Research Assistant in the BioNLP and Text Mining Lab at University of Delaware.Broadly, my research focus is on extracting information from biomedical documents using Natural Language Processing and Machine Learning principles. As part of my dissertation research, I have developed a relation extraction (RE) framework based on parsing and syntactic dependencies (Stanford CoreNLP, Semgrex) that automatically extracts certain general relations (such as Involvement, Regulation etc.) connecting a bio-entity (genes, microRNA) to associated biological concepts.This framework is motivated by general linguistics principles (Tree Adjoining Grammars) and also integrates extra-syntactic information such as negation, referential linking and semantic information. By leveraging this RE framework, I have developed several text-mining tools to extract (1) microRNA-disease associations and (2) differential expression information of genes in diseases. The different tools/programming languages that I use on a regular basis are listed below.Programming Language: Python, Java, Perl, Shell ScriptingWeb Development: Django, FlaskDatabase: mongoDB, MySQLOther: Docker, Google Protocol Buffer

Nature of work involves grading assignments and holding office hours
TA for CISC220 Data Structures (Fall 2011), CISC 320 Introduction to Algorithms(Spring 2012), CISC108 Introduction to Computer Science(Fall 2012), CISC 4/604 Logic and CISC 4/689 Machine Learning (Spring 2013)

- Working on Interra’s Vhdl Analyzer “Jaguar”. Involved in Product Development - Mainly involved in Bug-fixes, adding new VHDL 2008 enhancements/new features. Runtime Improvement of the Analyzer.Coding Language used: C/C++

Worked on studying and population of databases for security standards like Common Vulnerabilities and Exposures (CVE) and Common Platform Enumeration (CPE) and linking the two standards.Coding Language used: Ruby