Search Engines:
11-442 / 11-642
 
CMU logo
 

Fall 2024

Course
Description:
This lecture-oriented course studies the theory, design, and implementation of text-based search engines. The core components include statistical characteristics of text, representation of information needs and documents, several important lexical retrieval models, several recent neural models, and experimental evaluation. The course also covers common elements of commercial search engines, for example, integration of diverse search engines into a single search service (federated search, vertical search), personalized search results, and diverse search results. The software architecture components include design and implementation of large-scale, distributed search engines.

This is a full-semester course. The graduate section (11-642) is 12 units. The undergraduate section (11-442) is 9 units.

The main difference between the two sections (11-442, 11-642) is the amount of analysis, writing, and time required to complete homework assignments.
Learning Objectives: By the end of the course, students are expected to have developed the skills listed below.
  • Recall and discuss well-known search engine architectures, methods of representing text documents, methods of representing information needs, and methods of evaluating search effectiveness;
  • Implement well-known retrieval algorithms and test them on standard datasets; and
  • Apply information retrieval techniques discussed in class to solve problems faced by governments and companies.

Skills are assessed by the homework assignments; and by exams.

Eligibility: This course is open to all students who meet the prerequisites.
Prerequisites: This course requires good programming skills and an understanding of computer architectures and operating systems (e.g., memory vs. disk trade-offs). A basic understanding of probability, statistics, and linear algebra is helpful. Thus students should have preparation comparable to the following CMU undergraduate courses.
  • 15-210, Parallel and Sequential Data Structures and Algorithms (required)
  • 15-213, Introduction to Computer Systems (required)
  • 15-451, Algorithm Design and Analysis (helpful)
  • 21-241, Matrices and Linear Transformations or 21-341, Linear Algebra (required)
  • 21-325, Probability (required)
  • 36-202, Methods for Statistics & Data Science (helpful)
Homework assignments are done in the Python programming language, thus students must also have good Python programming skills.
Time &
Location:
Tu/Th 11:00 - 12:20 PM, Location NSH 3002
Instructors: Jamie Callan
Teaching Assistants:
Eleanor Shao xshao2@andrew
Siddharth Gandhi ssg2@andrew
Shreya Terupally sterupal@andrew
Zhen Fan zhenfan@andrew
Office hours:
Day Time Who Where
Monday 10:30-12:00
3:00-4:30
Shreya
Eleanor
Wean 3002
Zoom 9481423861
Tuesday 1:30-3:00 Siddharth Wean 3110
Wednesday 3:00-4:30 Eleanor Zoom 9481423861
Thursday 2:00-3:30 Shreya Wean 3002
Friday 2:00-3:30 Siddharth Wean 3110
Course
Materials:
Lecture Slides: Copies of the lecture slides are posted on this page, usually within 24 hours.

Textbook: The textbook is Introduction to Information Retrieval, Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schutze, Cambridge University Press. 2008. You may use the printed copy or the online copy, but note that the reading instructions refer to the printed copy.

Readings: There are additional selected readings, which will be available through the class web page (this page).

Piazza: A discussion forum is provided for students to ask questions, answer questions, and discuss class-related topics. The TAs monitor Piazza 11am-7pm M-F, and 3-7pm on the weekends. You must register yourself to access the discussion forum. Please provide a CMU email address when you join the discussion (you can use other email addresses, too). We will periodically remove people that do not have CMU email addresses.

Homework Services: A Homework Services web page provides information about your homework submissions and access to graded homework reports. Each individual homework has its own web pages that describe the assignment and provide access to automated testing services.

Restricted access: Online access to some materials (additional readings, lecture notes, datasets, etc) is restricted to CMU people. Students on CMU local and virtual private networking IP addresses have direct access. Other students can gain access using a password.
Homework: 5 assignments that give hands-on experience with techniques discussed in class. Homework must be done individually, and students may not share their work with other students. See the course Academic Integrity policy for more information.
Grading: 5 homework assignments (12% each, 60% total), midterm exam (20%), final exam (20%).
Grading
Scale:
Grades are assigned using a curve. Typically the median GPA is about 3.5.
Course
policies:
Academic Integrity, Attendance, Auditing, Generative AI, Laptops & mobile devices, Late homework, Pass/Fail, Waitlist
Syllabus:
Date Topic Readings
Aug 27, Introduction to search: Exact-match retrieval (pdf)
Aug 29, Introduction to search: DAAT, BM25, query operators (pdf) Ch 1, 11.4.3
Sep 2, HW1 out  
Sep 3, Introduction to search: QryEval (pdf)
HW1 integrity requirements (pdf)
Ch 2.4.2
Sep 4 Optional homework support session (pdf, mp4)
Time: 5:00-6:30, Location: GHC 6115
Sep 5, Evaluating search effectiveness (pdf) Ch 8-8.5
Sep 10, Best-match retrieval: VSM, Language models (pdf) Ch 6.2-6.4.2, Ch 12.2-12.4
Sep 12, Query structure: Information needs and queries (pdf)
Document representation (pdf)
Nguyen & Callan, 2011
Sep 16, HW1 due, HW2 out  
Sep 17, Query structure: Relevance and pseudo relevance feedback (pdf) Ch 9 - 9.2.2
Sep 19, Document representation (pdf) Ch 2 - 2.2
Sep 24, Index creation (pdf) Ch 4, Ch 5.3-5.3.1, Ch 2.3, Ch 7.1.3
Sep 26, Feature-based ranking models (pdf) Li, 2011
Sep 30, HW2 due, HW3 out  
Oct 1, Feature-based ranking models, Authority metrics (pdf) Ch 21 - 21.2
Oct 3, Large-scale indexes (pdf)  
Oct 8, Search logs
Oct 10, Midterm exam Sample Midterm, additional questions
Oct 22, Neural ranking models: Introduction  
Oct 24, Neural ranking models: BERT reranking Dai & Callan, 2019a
Oct 28, HW3 due, HW4 out  
Oct 29, Neural ranking models: Dense models Karpukhin, et al., 2020
Oct 31, Neural ranking models: Sparse models Dai & Callan, 2019b
Nov 7, Neural ranking models: Retrieval augmented generation Gao, et al., 2023
Nov 11, HW4 due, HW5 out  
Nov 12, Neural ranking models  
Nov 14, Recommender systems  
Nov 19, Recommender systems  
Nov 21, Diversity Santos, et al., 2010
Nov 25, HW5 due  
Nov 26, Diversity Dang & Croft, 2012
Dec 3, Personalization Bennett et al, 2012
Dec 5, Final exam Sample Final
Accommodations for Students with Disabilities: If you have a disability and are registered with the Office of Disability Resources, I encourage you to use their online system to notify me of your accommodations and discuss your needs with me as early in the semester as possible. I will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, I encourage you to contact them at access@andrew.cmu.edu.
If You Are Having
Difficulty:
If you are having difficulty in any of your courses, please consider reaching out to the Student Academic Success Center (SASC). SASC provides the following services.
  • Individual and small group coaching on the development of successful learning habits such as time management, stress reduction, and other skills (Academic Coaching).
  • Consultation for multilingual and international students (Language and Cross-Cultural Support).
  • Individual consultations and workshops to support excellence in communication of written texts, oral presentations, and data visualization (Communication Support).
Advice From
The Faculty:
This course is a lot of work. Take care of yourself. Do your best to maintain a healthy lifestyle this semester by eating well, exercising, avoiding drugs and alcohol, getting enough sleep and taking some time to relax. This will help you achieve your goals and cope with stress.

If you find yourself struggling with the material or workload, please ask for help. All of us benefit from support during times of struggle. You are not alone. There are many helpful resources available on campus and an important part of the college experience is learning how to ask for help. Asking for support sooner rather than later is often helpful.

If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support. Counseling and Psychological Services (CaPS) is here to help: call 412-268-2922 and visit their website at https://www.cmu.edu/counseling/. Consider reaching out to a friend, faculty or family member you trust for help getting connected to the support that can help.


Copyright 2024, Carnegie Mellon University.
Updated on October 03, 2024

Jamie Callan