MSc: Advanced Information Retrieval

Advanced Information Retrieval

• Course name: Advanced Information Retrieval
• Code discipline: CSE334
• Subject area: Computer systems organization; Information systems; Real-time systems; Information retrieval; World Wide Web

Short Description

This course covers the following concepts: Data indexing; Recommendations; Relevance and ranking.

Prerequisites

Prerequisite subjects

• CSE101 — Introduction to Programming I
• CSE102 — Introduction to Programming II
• CSE202 — Analytical Geometry and Linear Algebra I
• CSE204 — Analytic Geometry And Linear Algebra II: matrix multiplication, matrix decomposition (SVD, ALS) and approximation (matrix norm), sparse matrix, stability of solution (decomposition), vector spaces, metric spaces, manifold, eigenvector and eigenvalue.
• CSE113 — Philosophy I - (Discrete Math and Logic): graphs, trees, binary trees, balanced trees, metric (proximity) graphs, diameter, clique, path, shortest path.
• CSE206 — Probability And Statistics: probability, likelihood, conditional probability, Bayesian rule, stochastic matrix and properties.

Course Topics

Course Sections and Topics

Section	Topics within the section
Information retrieval basics	Introduction to IR, major concepts. Crawling and Web. Quality assessment.
Text processing and indexing	Building inverted index for text documents. Boolean retrieval model. Language, tokenization, stemming, searching, scoring. Spellchecking and wildcard search. Suggest and query expansion. Language modelling. Topic modelling.
Vector model and vector indexing	Vector model Machine learning for vector embedding Vector-based index structures
Advanced topics. Media processing	Image and video processing, understanding and indexing Content-based image retrieval Audio retrieval Relevance feedback

Intended Learning Outcomes (ILOs)

What is the main purpose of this course?

The course is designed to prepare students to understand background theories of information retrieval systems and introduce different information retrieval systems. The course will focus on the evaluation and analysis of such systems as well as how they are implemented. Throughout the course, students will be involved in discussions, readings, and assignments to experience real world systems. The technologies and algorithms covered in this class include machine learning, data mining, natural language processing, data indexing, and so on.

ILOs defined at three levels

Level 1: What concepts should a student know/remember/explain?

By the end of the course, the students should be able to ...

• Terms and definitions used in area of information retrieval,
• Search engine and recommender system essential parts,
• Quality metrics of information retrieval systems,
• Contemporary approaches to semantic data analysis,
• Indexing strategies.

Level 2: What basic practical skills should a student be able to perform?

By the end of the course, the students should be able to ...

• Understand background theories behind information retrieval systems,
• How to design a recommender system from scratch,
• How to evaluate quality of a particular information retrieval system,
• Core ideas and system implementation and maintenance,
• How to identify and fix information retrieval system problems.

Level 3: What complex comprehensive skills should a student be able to apply in real-life scenarios?

By the end of the course, the students should be able to ...

• Build a recommender service from scratch,
• Implement a proper index for an unstructured dataset,
• Plan quality measures for a new recommender service,
• Run initial data analysis and problem evaluation for a business task, related to information retrieval.

Grading

Course grading range

Grade	Range	Description of performance
A. Excellent	84-100	-
B. Good	72-83	-
C. Satisfactory	60-71	-
D. Poor	0-59	-

Course activities and grading breakdown

Activity Type	Percentage of the overall course grade
Assignments	60
Quizzes	40
Exams	0

Recommendations for students on how to succeed in the course

The simples way to succeed is to participate in labs and pass coding assignments in timely manner. This guarantees up to 60% of the grade. Participation in lecture quizzes allow to differentiate the grade.

Resources, literature and reference materials

Open access resources

• Manning, Raghavan, Schütze, An Introduction to Information Retrieval, 2008, Cambridge University Press
• Baeza-Yates, Ribeiro-Neto, Modern Information Retrieval, 2011, Addison-Wesley
• Buttcher, Clarke, Cormack, Information Retrieval: Implementing and Evaluating Search Engines, 2010, MIT Press
• Course repository in github.

Teaching Methodology: Methods, techniques, & activities

Activities and Teaching Methods

Activities within each section

Learning Activities	Section 1	Section 2	Section 3	Section 4
Development of individual parts of software product code	1	1	1	1
Homework and group projects	1	1	1	1
Testing (written or computer based)	1	1	1	1

Formative Assessment and Course Activities

Ongoing performance assessment

Section 1

Activity Type	Content	Is Graded?
Question	Enumerate limitations for web crawling.	1
Question	Propose a strategy for A/B testing.	1
Question	Propose recommender quality metric.	1
Question	Implement DCG metric.	1
Question	Discuss relevance metric.	1
Question	Crawl website with respect to robots.txt.	1
Question	What is typical IR system architecture?	0
Question	Show how to parse a dynamic web page.	0
Question	Provide a framework to accept/reject A/B testing results.	0
Question	Compute DCG for an example query for random search engine.	0
Question	Implement a metric for a recommender system.	0
Question	Implement pFound.	0

Section 2

Activity Type	Content	Is Graded?
Question	Build inverted index for a text.	1
Question	Tokenize a text.	1
Question	Implement simple spellchecker.	1
Question	Implement wildcard search.	1
Question	Build inverted index for a set of web pages.	0
Question	build a distribution of stems/lexemes for a text.	0
Question	Choose and implement case-insensitive index for a given text collection.	0
Question	Choose and implement semantic vector-based index for a given text collection.	0

Section 3

Activity Type	Content	Is Graded?
Question	Embed the text with an ML model.	1
Question	Build term-document matrix.	1
Question	Build semantic index for a dataset using Annoy.	1
Question	Build kd-tree index for a given dataset.	1
Question	Why kd-trees work badly in 100-dimensional environment?	1
Question	What is the difference between metric space and vector space?	1
Question	Choose and implement persistent index for a given text collection.	0
Question	Visualize a dataset for text classification.	0
Question	Build (H)NSW index for a dataset.	0
Question	Compare HNSW to Annoy index.	0
Question	What are metric space index structures you know?	0

Section 4

Activity Type	Content	Is Graded?
Question	Extract semantic information from images.	1
Question	Build an image hash.	1
Question	Build a spectral representation of a song.	1
Question	Whats is relevance feedback?	1
Question	Build a "search by color" feature.	0
Question	Extract scenes from video.	0
Question	Write a voice-controlled search.	0
Question	Semantic search within unlabelled image dataset.	0

Final assessment

Section 1

1. Implement text crawler for a news site.
2. What is SBS (side-by-side) and how is it used in search engines?
3. Compare pFound with CTR and with DCG.
4. Explain how A/B testing works.
5. Describe PageRank algorithm.

Section 2

1. Explain how (and why) KD-trees work.
2. What are weak places of inverted index?
3. Compare different text vectorization approaches.
4. Compare tolerant retrieval to spellchecking.

Section 3

1. Compare inverted index to HNSW in terms of speed, memory consumption?
2. Choose the best index for a given dataset.
3. Implement range search in KD-tree.

Section 4

1. What are the approaches to image understanding?
2. How to cluster a video into scenes and shots?
3. How speech-to-text technology works?
4. How to build audio fingerprints?

The retake exam

Section 1

1. Solve a complex coding problem similar to one of the homework or lab.

Section 2

1. Solve a complex coding problem similar to one of the homework or lab.

Section 3

1. Solve a complex coding problem similar to one of the homework or lab.

Section 4

1. Solve a complex coding problem similar to one of the homework or lab.