Atousa Pahlevan-Duprat, PhD

Me!

Welcome! I graduated form the department of computer science at the University of Victoria with a PhD degree in Software Engineering. I was a p

Welcome! I graduated form the department of computer science at the University of Victoria with a PhD degree in Software Engineering. I was a part of the Rigi group from 2007, under supervision of Dr. Hausi A. Müller. I got my Master of Mathematics from the University of Waterloo, at the Cheriton School of Computer Science in 2005, where I was part of the SWAG lab. My research expertise encompasses various domains within software engineering, with a focus on search, self-adaptive systems, and software architecture. My passion for information retrieval (IR) was ignited during my graduate studies at UVic, particularly through a data mining course. Since then, my work has spanned production search engines, optimizing search result relevancy, and implementing ranking algorithms using the Lucene search library. Currently, I am deeply engaged in exploring the capabilities of the RAG pipeline, which operates with Large Language Models (LLMs) trained on extensive datasets, covering a multitude of attributes. This endeavor offers an exciting opportunity to apply advanced Natural Language Processing (NLP) techniques to enhance information retrieval processes. In Addition, preparing multimodal datasets involves distinct data collection and preprocessing for each modality, alongside the critical task of aligning and normalizing data for compatibility, posing significant challenges due to format, temporal, and semantic variations. Embedding independent models based on their semantic similarity into one vector space and building a multi-model search in RAG is one of the areas I am delving into.

Time is always right to do right
Martin Luther King Jr. at Stanford, 1967.