Course enquiries
Course Email
Course overview
- Study period
- Semester 2, 2026 (27/07/2026 - 21/11/2026)
- Study level
- Postgraduate Coursework
- Location
- St Lucia
- Attendance mode
- In Person
- Units
- 2
- Administrative campus
- St Lucia
- Coordinating unit
- Elec Engineering & Comp Science School
The course discusses the theory, design, and implementation of Information Retrieval (IR) techniques in text-based information systems. The theoretical component of the course focuses on IR methods for the processing, indexing, querying, ranking, organisation, and classification of textual documents, including Web documents. A variety of current research topics are also covered, including professional search and recommendation systems. The practical component of the course addresses the design and implementation of high-capacity text retrieval and filtering systems such as web search engines.
The ubiquity of text-based information systems (e.g., Web search engines, online advertising, and recommender systems) is fuelling the rapid growth of interest in studying various topics in the area of Information Retrieval (IR). The remarkable success of search engines like Google, Bing and the likes is a striking example of how important it is for academia and industry to foster innovation in the field of IR and text-based information systems. This course will cover various IR techniques that are employed in building a complete text-based information system, including recent advances in large language models for IR, retrieval-augmented generation (RAG), and agentic approaches to search.
AI tools may be used in this course, and students receive guidance on acceptable use, attribution or disclosure. Students are responsible for ensuring that any use of AI complies with academic integrity requirements and is appropriately acknowledged.
In response to student feedback from previous offerings, this course has been updated to include more coverage of recent developments in information retrieval, including text diffusion models and agentic approaches to search. Weekly quizzes and practical activities in the early weeks of semester will provide students with feedback on their understanding before the Census date.
Course requirements
Assumed background
Background in data managements (e.g.,ﾠSQL and indexing),ﾠprobability and statistics, algorithms and data structures;ﾠsolid programming skillsﾠ(Python) and algorithmical thinking.
Prerequisites
You'll need to complete the following courses before enrolling in this one:
INFS2200 or INFS7903
Course contact
Course staff
Course coordinator
Dr Shuai Wang
Lecturer
Dr Shuai Wang
Guest lecturer
Dr Hang Li
Dr Joel Mackenzie
Timetable
The timetable for this course is available on the UQ Public Timetable.
Aims and outcomes
The aim of this course is to provide a comprehensive introduction to Information Retrieval (IR). The areas covered include data acquisition andﾠpre-processing (crawling, stemming), indexing, querying, ranking, organisation and representation of textual documents, evaluation. The goal is to present fundamental concepts and algorithms for each topic, thus providing the students with the necessary background and practical skills for the application of information retrieval in web search engines. In addition, this course also provides a starting point for those students who are interested in pursuing research in information retrieval or related fields.
Learning outcomes
After successfully completing this course you should be able to:
LO1.
Gain in-depth knowledge of the core principles in the information retrieval field such as text representation and similarity computation, indexing textual documents, query correction and expansion, retrieval models, performance evaluation and metrics
LO2.
Acquire hands-on practical experience with the development of components of Web search engines and experimentation of end-to-end systems using relevant open-source libraries.
LO3.
Understand advanced topics in information retrieval research such as learning to rank, neural retrieval and ranking.
LO4.
Create, analyse and evaluate novel information retrieval solutions to search related problems
LO5.
Compare and contrast information retrieval methods and communicate their differences, advantages and disadvantages, based on quantitative evaluation.
LO6.
Analyse search tasks and problems, and identify and communicate relevant information retrieval solutions.
Assessment
Assessment summary
| Category | Assessment task | Weight | Due date |
|---|---|---|---|
| Quiz |
Weekly quizzes
|
10% |
31/07/2026 4:00 pm 7/08/2026 4:00 pm 14/08/2026 4:00 pm 21/08/2026 4:00 pm 28/08/2026 4:00 pm 4/09/2026 4:00 pm 11/09/2026 4:00 pm 18/09/2026 4:00 pm 25/09/2026 4:00 pm 9/10/2026 4:00 pm 16/10/2026 4:00 pm 23/10/2026 4:00 pm 30/10/2026 4:00 pm |
| Computer Code, Paper/ Report/ Annotation, Project |
Project Part 1
|
10% |
4/09/2026 4:00 pm |
| Computer Code, Paper/ Report/ Annotation, Project |
Project Part 2
|
30% |
30/10/2026 4:00 pm |
| Examination |
Final Oral Exam
|
50% |
9/11/2026 - 20/11/2026 |
A hurdle is an assessment requirement that must be satisfied in order to receive a specific grade for the course. Check the assessment details for more information about hurdle requirements.
Assessment details
Weekly quizzes
- Online
- Mode
- Written
- Category
- Quiz
- Weight
- 10%
- Due date
31/07/2026 4:00 pm
7/08/2026 4:00 pm
14/08/2026 4:00 pm
21/08/2026 4:00 pm
28/08/2026 4:00 pm
4/09/2026 4:00 pm
11/09/2026 4:00 pm
18/09/2026 4:00 pm
25/09/2026 4:00 pm
9/10/2026 4:00 pm
16/10/2026 4:00 pm
23/10/2026 4:00 pm
30/10/2026 4:00 pm
- Learning outcomes
- L01, L03
Task description
Online Quizzes on Blackboard. To be completed individually.
The early weekly quizzes and practical activities provide students with feedback on their understanding before the Census date.
Generative AI and Machine Translation in Assessment
Artificial Intelligence (AI) and Machine Translation (MT) tools may be used to support learning and preparation for this assessment task. However, students are expected to complete each quiz individually and to submit answers that reflect their own understanding.
Students must not use AI, MT, or other tools in a way that misrepresents their own knowledge or independent work. Inappropriate use of AI or MT may constitute student misconduct under the Student Code of Conduct.
Assessment security
Open assessment: In this assessment you can use resources such as your notes, course materials, and other tools, including AI, while completing the task. The focus is not on memorising information, but on understanding, applying judgement, and demonstrating your own thinking.
Submission guidelines
Deferral or extension
You cannot defer or apply for an extension for this assessment.
Because only the best 10 of 13 will contribute to the mark for this assessment item and results/answers are released soon after the due date, no extensions are permitted.
Late submission
You will receive a mark of 0 if this assessment is submitted late.
Because the results/answers are released soon after the due date, and only the best 10 of 13 will contribute to the mark for this assessment item a 100% penalty will be applied to late submission.
This has been approved by the Associate Dean (Academic)
Project Part 1
- Online
- Mode
- Product/ Artefact/ Multimedia, Written
- Category
- Computer Code, Paper/ Report/ Annotation, Project
- Weight
- 10%
- Due date
4/09/2026 4:00 pm
- Learning outcomes
- L02, L04, L05, L06
Task description
This project requires students to implement a set of identified indexing and retrieval methods. The students also need to evaluate and analyse the results of the techniques.
This is an individually assessed project.
Generative AI and Machine Translation in Assessment
Artificial Intelligence (AI) and Machine Translation (MT) are emerging tools that may support students in completing this assessment task. Students may appropriately use AI and/or MT in completing this assessment task. Students must clearly reference any use of AI or MT in each instance. A failure to reference generative AI or MT use may constitute student misconduct under the Student Code of Conduct.
Assessment security
Open assessment: In this assessment you can use resources such as your notes, course materials, and other tools, including AI, while completing the task. The focus is not on memorising information, but on understanding, applying judgement, and demonstrating your own thinking.
Submission guidelines
UQ Blackboard Online Submission
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
Extensions are limited to 7 days as feedback will be provided within 14 days.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Project Part 2
- Online
- Mode
- Product/ Artefact/ Multimedia, Written
- Category
- Computer Code, Paper/ Report/ Annotation, Project
- Weight
- 30%
- Due date
30/10/2026 4:00 pm
- Learning outcomes
- L02, L04, L05, L06
Task description
This project requires students to implement a set of identified indexing and retrieval methods. The students also need to evaluate and analyse the results of the techniques.
This is an individually assessed project.
Generative AI and Machine Translation in Assessment
Artificial Intelligence (AI) and Machine Translation (MT) are emerging tools that may support students in completing this assessment task. Students may appropriately use AI and/or MT in completing this assessment task. Students must clearly reference any use of AI or MT in each instance. A failure to reference generative AI or MT use may constitute student misconduct under the Student Code of Conduct.
Assessment security
Open assessment: In this assessment you can use resources such as your notes, course materials, and other tools, including AI, while completing the task. The focus is not on memorising information, but on understanding, applying judgement, and demonstrating your own thinking.
Submission guidelines
UQ Blackboard Online Submission
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
Extensions are limited to 7 days as feedback will be provided within 14 days.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Final Oral Exam
- Hurdle
- Identity Verified
- In-person
- Mode
- Oral
- Category
- Examination
- Weight
- 50%
- Due date
9/11/2026 - 20/11/2026
- Other conditions
- Secure.
- Learning outcomes
- L01, L03, L05, L06
Task description
All topics taught in the course will be covered. In accordance with UQ Assessment Policy, your oral examination will be recorded.
Generative AI and Machine Translation in Assessment
This assessment task is to be completed in-person. The use of generative Artificial Intelligence (AI) or Machine Translation (MT) tools will not be permitted. Any attempted use of AI or MT may constitute student misconduct under the Student Code of Conduct.
Assessment security
Secure assessment: This assessment is designed to protect academic integrity and assess your understanding of course concepts. You must only use the approved materials and tools for this assessment task. Use of prohibited materials in this task may be investigated and treated as academic misconduct. See assessment instructions for more details.
Hurdle requirements
To pass this course, a minimum of 50% must be obtained in the final exam. To achieve a grade of 3 and be eligible for supplementary assessment, students must achieve greater than 30% in the Final Oral Exam. Students who achieve 30% or less in the Final Oral Exam will have their final grade capped at 2, regardless of performance in other assessment items.Exam details
| Planning time | no planning time minutes |
|---|---|
| Duration | 30 minutes |
| Calculator options | No calculators permitted |
| Open/closed book | Closed book examination - no written materials permitted |
| Exam platform | Other |
| Invigilation | Invigilated in person |
Submission guidelines
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
If you are unable to attend the Final Oral Exam during your scheduled assessment time, you must submit an Extension of Assessment Due Date request through my.UQ. Students with approved extension requests will be offered one rescheduled assessment time for the Final Oral Exam.
Course grading
Full criteria for each grade is available in the Assessment Procedure.
| Grade | Cut off Percent | Description |
|---|---|---|
| 1 (Low Fail) | 0 - 19 |
Absence of evidence of achievement of course learning outcomes. |
| 2 (Fail) | 20 - 44 |
Minimal evidence of achievement of course learning outcomes. |
| 3 (Marginal Fail) | 45 - 49 |
Demonstrated evidence of developing achievement of course learning outcomes |
| 4 (Pass) | 50 - 64 |
Demonstrated evidence of functional achievement of course learning outcomes. |
| 5 (Credit) | 65 - 74 |
Demonstrated evidence of proficient achievement of course learning outcomes. |
| 6 (Distinction) | 75 - 84 |
Demonstrated evidence of advanced achievement of course learning outcomes. |
| 7 (High Distinction) | 85 - 100 |
Demonstrated evidence of exceptional achievement of course learning outcomes. |
Additional course grading information
The final percentage for the course is calculated by combining all assessment components: weekly quizzes 10%, Project Part 1 10%, Project Part 2 30%, and the Final Oral Exam 50%.
To pass this course, students must obtain at least 25 out of 50 marks, equivalent to 50%, in the Final Oral Exam. Students who do not meet this hurdle requirement will not be eligible for a passing grade, regardless of their overall course percentage.
To achieve a grade of 3 and be eligible for supplementary assessment, students must achieve greater than 30% in the Final Oral Exam, equivalent to greater than 15 out of 50 marks. Students who achieve 30% or less in the Final Oral Exam will have their final grade capped at 2, regardless of performance in other assessment items.
The final course percentage will be rounded up to the next whole number before final grade cut-offs are applied. For example, a final course percentage of 84.1% will be rounded up to 85%, resulting in a grade of 7. Hurdle requirements and supplementary assessment eligibility requirements are applied using the unrounded mark for the relevant assessment item.
Supplementary assessment
Supplementary assessment is available for this course.
Additional assessment information
Having Troubles?
If you are having difficulties with any aspect of the course material, you should seek help. Speak to the course teaching staff.
If external circumstances are affecting your ability to work on the course, you should seek help as soon as possible. The University and UQ Union have organisations and staff who are able to help, for example, UQ Student Services are able to help with study and exam skills, tertiary learning skills, writing skills, financial assistance, personal issues, and disability services (among other things).
Complaints and criticisms should be directed in the first instance to the course coordinator. If you are not satisfied with the outcome, you may bring the matter to the attention of the School of EECS Director of Teaching and Learning.
Learning resources
You'll need the following resources to successfully complete the course. We've indicated below if you need a personal copy of the reading materials or your own item.
Library resources
Find the required and recommended resources for this course on the UQ Library website.
Additional learning resources information
Course material will be published on the course website. Additional recommended readings
* Bhaskar Mitra, and Nick Craswell. "An introduction to neural information retrieval." Foundations and Trends® in Information Retrieval 13.1 (2018): 1-126. Available at https://www.microsoft.com/en-us/research/wp-content/uploads/2017/06/INR-061-Mitra-neuralir-intro.pdf
* Nicola Tonellotto. "Lecture notes on neural information retrieval." arXiv preprint arXiv:2207.13443 (2022). Available at https://arxiv.org/pdf/2207.13443
Learning activities
The learning activities for this course are outlined below. Learn more about the learning outcomes that apply to this course.
Filter activity type by
Please select
| Learning period | Activity type | Topic |
|---|---|---|
Multiple weeks From Week 1 To Week 13 |
Practical |
Practicals Practicals will provide an opportunity to further understand the concepts and techniques introduced in the lectures via examples, exercises, projects and problem-solving. Further concepts will be developed during these activities. There will be a mix of theory and hands-on activities. NOTE: these sessions start from week 1 and run until week 13 included. Learning outcomes: L02, L04, L05, L06 |
Week 1 (27 Jul - 02 Aug) |
Lecture |
Intro, Search Engine Architecture, Text Analysis Introduction, Motivation and Logistic. Architecture of a Search Engine, key components of study across this course. Zipf's Law, Stemming, Stopwording. Indexing techniques and processing, including data structures. Learning outcomes: L01, L04, L05 |
Week 2 (03 Aug - 09 Aug) |
Lecture |
Offline Evaluation Offline evaluation methodology and evaluation frameworks, set-based and rank-based evaluation measures, statistical significance testing, parameter tuning. Learning outcomes: L01, L04, L05, L06 |
Week 3 (10 Aug - 16 Aug) |
Lecture |
Retrieval Models 1 Types of Retrieval models, Lexical-based models based on term frequency, Term Frequency-Inverse Document Frequency, BM25, QLM. Learning outcomes: L01, L03, L05 |
Week 4 (17 Aug - 23 Aug) |
Lecture |
Retrieval Models 2 Encoder and Decoder, Pre-trained language models, Transformers Learning outcomes: L01, L03, L05 |
Week 5 (24 Aug - 30 Aug) |
Lecture |
Retrieval Models 3 Lexical-based Retrieval models with Learned term weight; TILDE, SPLADE Learning outcomes: L01, L03, L05 |
Week 6 (31 Aug - 06 Sep) |
Lecture |
Retrieval Models 4 Embedding-based Retrieval models; RepBERT, ANCE, DPR, Contriver, COLBERT, Repllama; Learning outcomes: L03, L05 |
Week 7 (07 Sep - 13 Sep) |
Lecture |
Reranking Models 1 Offline Learning to rank and Online Learning to rank: Exploit Implicit Signals, counterfactual learning, online evaluation, click models Learning outcomes: L01, L03, L05 |
Week 8 (14 Sep - 20 Sep) |
Lecture |
Reranking Models 2 BERT-based Rerankers: MonoBERT, DuoBERT, LLM-based rerankers; Pointwise, PairWise, ListWise, SetWise Learning outcomes: L03, L05 |
Week 9 (21 Sep - 27 Sep) |
Lecture |
Information Retrieval in the Age of LLMs Generative-IR, Vision Language Models, Screenshot retriever, Diffusion-model based retriever. Learning outcomes: L03, L05, L06 |
Week 10 (05 Oct - 11 Oct) |
Lecture |
Information Retrieval in the Age of LLMs - 2 Retrieval-augmented Generation, REACT, Search Agent, LLM Harness. Learning outcomes: L03, L05 |
Week 11 (12 Oct - 18 Oct) |
Lecture |
Other Ranking Models: Diversity IR, Crawling and Link Analysis Ranking methods for diversity, ambiguity and redundancy. Methods for crawling Web pages; making use of link information: PageRank and HITS. Learning outcomes: L01, L05 |
Week 12 (19 Oct - 25 Oct) |
Lecture |
Relevance Feedback and Fusion Methods based on query analysis, query expansion, relevance feedback. Fusion Methods Learning outcomes: L01, L05 |
Week 13 (26 Oct - 01 Nov) |
Lecture |
Index Compression Methods for compression: delta encoding, bit aligned codes, byte aligned codes Learning outcomes: L01, L05, L06 |
Policies and procedures
University policies and procedures apply to all aspects of student life. As a UQ student, you must comply with University-wide and program-specific requirements, including the:
- Student Code of Conduct Policy
- Student Integrity and Misconduct Policy and Procedure
- Assessment Procedure
- Examinations Procedure
- Reasonable Adjustments for Students Policy and Procedure
- AI for Assessment Guide
- Recording of Teaching Policy and Procedure
Learn more about UQ policies on my.UQ and the Policy and Procedure Library.
School guidelines
Your school has additional guidelines you'll need to follow for this course: