Course Description

Information retrieval (IR) methods are an indispensable tool in the current landscape of exponentially increasing text-based information, especially on the Web. Conventionally, IR tasks involves fetching and ranking a set of documents from a large corpus in terms of relevance to a user's information need. IR has been one of the most important problems in the domain of natural language processing (NLP). The application of IR techniques has been evolved with the advances of machine learning (deep learning) and data science.

D2L

D2L will be used only for submitting, grading assignments, and discussion. Also, announcements will be sent via D2L. We may use quiz feature in D2L for the problem sets (TBD). Your first go-to for this course is this website. Please, refer to this website before any other resources.

Topics

This course covers fundamental theories and essential techniques for building text-based information retrieval systems, including the following topics:

• Crawling
• Text processing techniques
• Indexing
• Retrieval models
• Evaluation methods
• Link analysis
• Relevance feedback
• Recommender systems
• Machine learning-based approaches for IR
• Deep learning applications

Prerequisites

CS 3305 and (CS 3410 or CSE 3153)
Students need to be familiar with basic algebra, calculus, probability and statistics.

Proficiency in Python
Students should be familiar with programming in Python. All the assignments and lecture demos will be in Python.

Textbook

Textbooks are available online. It is recommended to read the textbook sections specified in the course schedule table and also the additional recommended reading materials.

• [IR] Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press 2008.
• [SE] W. Bruce Croft, Donald Metzler, Trevor Strohman, Search Engines -- Information Retrieval in Practice, 2015