Debaditya Pal

Background

About Debaditya Pal

I am pursuing my master's degree in Computer Science at the University of Southern California, where I work with Dr. David Traum on natural language dialogue systems. My research focuses on grounding methods for generative dialogue, knowledge graph creation from text corpora, and persona-based versus knowledge graph-based grounding for fluidity and reduced hallucination rates. I have published my research findings at reputable conferences, such as FLAIRS and TENCON, and received a nomination for the best student paper award.Besides my academic work, I have also gained valuable industry experience as a software engineer. I recently led a three-member team at Sogage Software, where we analyzed customer data from Discord and Twitter using Google Cloud NLP toolkit, and provided insights to increase post engagement and user interaction. We also revamped the intra-application messaging system by employing Google Pub/Sub and Google Cloud Scheduler, improving runtime efficiency by 20%. Previously, I worked as an NLP intern at USC Institute for Creative Technologies, where I compared different transformer-based encoders for low latency information retrieval and ranking. I have also completed multiple certifications in machine learning and deep learning from Stanford University and deeplearning.ai. I am passionate about creating innovative and impactful NLP and DL solutions, and I am always eager to learn new skills and technologies.