MSc: Advanced Information Retrieval
Revision as of 11:42, 29 August 2022 by R.sirgalina (talk | contribs)
Advanced Information Retrieval
- Course name: Advanced Information Retrieval
- Code discipline: N/A
- 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.
- Analysis: DFT, [discrete] gradient.
- 3blue1brown playlist on Linear Algebra can help to overview selected topics.
- Actually, on their channel you can find almost any maths topic, e.g. Fourier Transform.
- Gilbert Strang is one of the best human teachers of Algebra, if you prefer classic lectures to fancy videos.
- This MIT course can help you with discrete objects.
- For Russian readers there is a maths book from the course author with labs.
- Also there is a very basic python-based course on maths with lots of relevant (and irrelevant) labs.
- To have a better feeling of networking, please refer to this video lecture.
- Kick start your numpy with the official quickstart guide.
Prerequisite topics
Course Topics
| Section | Topics within the section |
|---|---|
| Introduction. Crawling and quality basics |
|
| Text indexing and language processing |
|
| Advanced index data structures |
|
| Advanced retrieval topics. Media retrieval |
|
Intended Learning Outcomes (ILOs)
What is the main purpose of this course?
The course is designed to prepare students to understand and learn contemporary tools of information retrieval systems. Students, who will later dedicate their engineering or scientific careers to implementation of search engines, social networks, recommender systems and other content services will obtain necessary knowledge and skills in designing and implementing essential parts of such systems.
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 ...
- 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 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 | 70-83 | - |
| C. Satisfactory | 60-69 | - |
| D. Poor | 0-59 | - |
Course activities and grading breakdown
| Activity Type | Percentage of the overall course grade |
|---|---|
| Labs/seminar classes | 30 |
| Interim performance assessment | 0 |
| Assessments (homework) | 70 |
| Exams | 0 |
Recommendations for students on how to succeed in the course
Resources, literature and reference materials
Open access resources
- "An Introduction to Information Retrieval" by Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Cambridge University Press (any edition)
- “Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit,” Steven Bird, Ewan Klein, and Edward Loper. [link]
Closed access resources
Software and tools used within the course
Teaching Methodology: Methods, techniques, & activities
Activities and Teaching Methods
| 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 |
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 | 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 | Embed the text with a model. | 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 persistent index for a given text collection. | 0 |
| Question | Visualize a dataset for text classification. | 0 |
Section 3
| Activity Type | Content | Is Graded? |
|---|---|---|
| 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 | 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
- Implement text crawler for a news site.
- What is SBS (side-by-side) and how is it used in search engines?
- Compare pFound with CTR and with DCG.
- Explain how A/B testing works.
Section 2
- Explain how (and why) KD-trees work.
- What are weak places of inverted index?
- Compare different text vectorization approaches.
- Compare tolerant retrieval to spellchecking.
Section 3
- Compare inverted index to HNSW in terms of speed, memory consumption?
- Choose the best index for a given dataset.
- Implement range search in KD-tree.
Section 4
- What are the approaches to image understanding?
- How to cluster a video into scenes and shots?
- How speech-to-text technology works?
- How to build audio fingerprints?
The retake exam
Section 1
Section 2
Section 3
Section 4