COMPSCI 646 is a graduate-level course in Information Retrieval, the science and engineering of organizing, searching, and making sense of large amounts of mostly unstructured (typically textual) data. The impact of IR research is most visible from the Web search engines, where many people actively interact with IR systems, but IR research goes beyond Web search. The class focuses primarily on the theory, design, and implementation of effective models for information organization and retrieval. The course also covers current research problems and methodologies in the field of IR.

Course Information

Instructor: Razieh Negin Rahimi

Email: rahimi+cs646@cs[dot]umass[dot]edu
Office hours: Monday/Wednesday 10:30-11:30am EDT in Zoom

Teaching Assistant: Chen Qu

Email: chenqu@cs[dot]umass[dot]edu
Office hours: Thursday 10:30-11:30am EDT in Zoom

Grader: Hiba Ahsan

Email: hahsan@umass[dot]edu
Office hours: Friday 10:30-11:30am EDT in Zoom

Grader: Shibin George

Email: shibingeorge@umass[dot]edu
Office hours: Friday 10:30-11:30am EDT in Zoom




Resources to get familiar with neural networks:

Previous offerings


Assignments (3 * 15%)

All assignments contain both written questions and programming parts, and are due on either a Tuesday or a Friday at 5:00 pm AOE.
Assignments are submitted via Gradescope.

Midterm Exam (15%)

Final Exam (15%)

Final Project (25%)

Extra Credit Points for Participation (4%)


Date Description Course Materials Events Deadlines
Mon Aug. 24 Introduction
Wed Aug. 26 Evaluation [IIR] Ch.8
Mon Aug. 31 Evaluation (cont'd)
Text Processing and Indexing

[SE] Ch.4.1-4.3
[SE] Ch.5.1-5.4
Wed Sep. 2 Text Processing and Indexing [IIR] Ch.4, Ch.5
Mon Sep. 7 Vector Space Model [IIR] Ch.6.2-6.4
Wed Sep. 9 Probabilistic Retrieval Models [IIR] Ch.11.1-11.4
Mon Sep. 14 Statistical Language Models [IIR] Ch.12.1-3
Wed Sep. 16 Relevance Feedback [SE] Ch.7.3.2
Mon Sep. 21 Learning to Rank LTR ref: Hang Li (2011) Ch.1, 2, Ch.6 (optional)
Wed Sep. 23 Implicit feedback and click models Click Models for Web Search, Chuklin et al. (2015) Ch. 3
Mon Sep. 28 Latent Semantic Indexing
Distributed Word Representations
[IIR] Ch.18
Word2vec: Mikolov et al. (NIPS 2013)
(optional) GloVe: Pennington et al. (EMNLP 2014)
Wed Sep. 30 Distributed Word Representations for IR
Mon Oct. 5 Recurrent Neural Networks and Transformer
Wed Oct. 7 Contextual Word Representations
Mon Oct. 12 Neural Ranking Models
Wed Oct. 14 Recommender Systems
Mon Oct. 19 Link Analysis
Wed Oct. 21 Personalization and Context-Aware Search
Mon Oct. 26 Diversity
Wed Oct. 28 Question Answering
Mon Nov. 2 Conversation and Dialogue Systems
Wed Nov. 4 User Study and Crowdsourcing
Mon Nov. 9 Cross-Language Information Retrieval
Wed Nov. 11 IR Applications
Mon Nov. 16 IR Applications
Wed Nov. 18 IR Applications


Late Submission

Each student has a total of 6 late days without penalty. You can use up to 3 late days per assignment or project milestone excluding project final report. Late submission of team assignments will result in each member of the team being charged for the late days. For example, if a group of two students submitted their project proposal 23 hours after the deadline, this results in 1 late day being used per student.

Once all 6 late days are used, any assignments turned in late will be penalized 20% per late day.

In case of multiple submissions of an assignment, only the last one will be taken into account for the number of late days.

Collaboration and Help

You may discuss the ideas behind assignments with others. You may ask for help understanding class and IR concepts. You may study with friends. However...

The work that you submit must be your own. It may not be copied from the web, from another student in the class, or from anyone else. If you stumble upon and use a solution from the textbook or from class, you are expected to acknowledge the source of the work.

Your effort on exams (mini or final) must be your own. Your homework submissions must be your own work and not in collaboration with anyone. Your project work must be your own work and not a copy of someone else's work.

Helpful UMass Resources