This course delves deep into text-based information retrieval (IR) techniques, offering a comprehensive look at search engines. It begins with the fundamentals of conceptual models of IR, including the Boolean model, and will delve into tokenization and text analysis. Throughout the course, students will be exposed to various IR models. These include the Boolean, vector space, and probabilistic models. It explores efficient indexing techniques and methods for indexing general document collections. The course will also touch upon vital components like scoring and ranking in IR systems and introduce students to embeddings and Latent Semantic Indexing (LSI). It touches upon the basics of deep learning for IR, the role of transformers in IR, and the evaluation methodologies in the field. The power of web search and crawling will be studied, along with link analysis techniques such as PageRank and HITS.

The course will deeply explore word vectors such as Word2Vec, GloVe, and Doc2Vec alongside cutting-edge topics like large language models and using RAG(Retrieval-Augmented Generation) for question-answering. Students will also learn about recommendation systems and collaborative filtering. Emphasis will be on hands-on projects using the GCP to bolster practical IR skills. Concluding the course, students will present their projects, bridging theory with practice. This course is foundational for understanding IR and paves the way for advanced classes like CSE 635, focusing on NLP and text mining.