Course coordinator
Professor Shane Culpepper
Course overview
- Study period
- Semester 2, 2025 (28/07/2025 - 22/11/2025)
- Study level
- Undergraduate
- Location
- St Lucia
- Attendance mode
- In Person
- Units
- 2
- Administrative campus
- St Lucia
- Coordinating unit
- Elec Engineering & Comp Science School
The Internet has transformed much of the world's knowledge into unstructured text, and the amount of data being made available every day continues to grow exponentially. Developing new techniques to turn this data into knowledge is crucial in the age of information. Processing natural language text is both challenging and rewarding. Learning how to work with web-scale data collections is a critical skill to develop in Computer Science, and understanding the computational methods currently available to achieve scalable data processing will position students to be innovators in AI technologies in their future careers. This course will explore state-of-the-art techniques in natural language understanding and language generation. Students will develop an understanding of the key algorithms used in natural language processing, and be exposed to a diverse range of applications including machine translation, text mining, sentiment analysis, and question answering. Python will be used extensively in this course, and so students are expected to have an intermediate level of knowledge with Python programming.
Changes to this offering include improvements to weekly lectures and addition of a new lecture in week 12.
Course requirements
Assumed background
Intermediate programming ability in Python
Some exposure to linear algebra and calculus
Some exposure to machine learning
Prerequisites
You'll need to complete the following courses before enrolling in this one:
MATH1061 and (STAT1201 or STAT1301 or STAT2203 or STAT2003 or STAT2201) and (CSSE1001 or ENGG1001)
Recommended prerequisites
We recommend completing the following courses before enrolling in this one:
(COMP3710 or COMP4702) and (MATH1051 OR MATH1071)
Course contact
Course staff
Lecturer
Professor Shane Culpepper
Timetable
The timetable for this course is available on the UQ Public Timetable.
Additional timetable information
Aims and outcomes
This course aims to equip students from a wide variety of backgrounds and disciplines with awareness and knowledge in Computer Science and Generative AI.
In this course students will learn:
- Text classification and unsupervised topic discovery
- Similarity measures for natural language text
- Part of speech and named entity tagging
- Parsing Sentence structure and syntax
- N-gram language modelling and coreference resolution
- Machine Translation Techniques
- Word Vectors and Deep Learning Basics
- Advanced text modelling (RNN,Seq2seq, Transformers)
On completing this subject, students should have the following skills:
- Create and apply algorithmic solutions to computational problems by referencing current research literature.
- Understand solutions to complex problems, and analyze their operational efficiency.
- Create, implement and evaluate programs for small and medium size problems in the Python programming language.
Learning outcomes
After successfully completing this course you should be able to:
LO1.
Describe and discuss key concepts in Natural Language Processing.
LO2.
Create computational models of natural language based on the concepts learned in the course.
LO3.
Evaluate the mathematical and/or algorithmic basis of common NLP techniques.
LO4.
Apply relevant techniques and/or interface with existing python APIs.
LO5.
Create end-to-end research experiments, including evaluation of text corpora as well as presentation and interpretation of results.
LO6.
Critically analyze and evaluate state-of-the-art text processing systems and communicate criticisms clearly.
Assessment
Assessment summary
| Category | Assessment task | Weight | Due date |
|---|---|---|---|
| Quiz |
Weekly Quiz
|
10% Best 5 of 7 (2% per quiz) |
8/08/2025 3:00 pm 15/08/2025 3:00 pm 22/08/2025 3:00 pm 5/09/2025 3:00 pm 12/09/2025 3:00 pm 26/09/2025 3:00 pm 24/10/2025 3:00 pm |
| Computer Code | Assignment 1 | 15% |
29/08/2025 3:00 pm |
| Computer Code, Paper/ Report/ Annotation | Assignment 2 | 25% |
24/10/2025 3:00 pm |
| Examination |
Final Exam
|
50% |
End of Semester Exam Period 8/11/2025 - 22/11/2025 |
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 Quiz
- Online
- Mode
- Written
- Category
- Quiz
- Weight
- 10% Best 5 of 7 (2% per quiz)
- Due date
8/08/2025 3:00 pm
15/08/2025 3:00 pm
22/08/2025 3:00 pm
5/09/2025 3:00 pm
12/09/2025 3:00 pm
26/09/2025 3:00 pm
24/10/2025 3:00 pm
- Other conditions
- Time limited.
Task description
Online short answer, multiple choice, true/false, and computational questions related the previous lectures.
The best 5 of 7 quizzes will be used to calculate the student mark for this assessment.
Artificial Intelligence (AI) and Machine Translation (MT) tools may be used for this assignment.
Note that all assignments are to be worked on individually and must be your own work except where the use of code written or provided by other entities (teaching staff, AI tools, etc.) is explicitly permitted by the assignment specification. Artificial Intelligence (AI) and Machine Translation (MT) tools are permitted to be used in the programming assignments in this course, but they are not required to be used and not recommended to be used as they may inhibit learning and introduce bugs into your code. You must always follow the referencing requirements set out in the assignment specification and documents referenced from the assignment specification. Failure to appropriately reference the resources (tools and information sources) used in your work may result in misconduct allegations against you. You are encouraged to discuss the concepts behind the assignments but under no circumstances should you show your code to, or allow your code to be seen by, another student. You should not look at the code of any other student. You must sufficiently protect all electronic and paper copies of your code. All submitted code will be subject to electronic plagiarism and collusion detection. Assignments with no academic merit will be awarded a mark of zero. You may have to verbally answer questions about your submission as part of the assignment marking process.ﾠ
Submission guidelines
Submitted online using GradeScope.
Deferral or extension
You cannot defer or apply for an extension for this assessment.
Because only the best 5 of 7 quizzes will contribute to the mark for this assessment item and results/answers are released soon after the due date, no extensions are permitted.
If a student - who has had valid reasons for an extension - has not submitted at least 5 quizzes by the end of semester, they will have their quiz score weighted at n *2% (where n is the number of problem sets submitted), and their final exam weight will be increased by (5-n) * 2%.
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 5 of 7 will contribute to the mark for this assessment item, a 100% penalty will be applied to late submissions. This has been approved by the Associate Dean (Academic).
Assignment 1
- Mode
- Product/ Artefact/ Multimedia
- Category
- Computer Code
- Weight
- 15%
- Due date
29/08/2025 3:00 pm
- Learning outcomes
- L02, L03, L04
Task description
The first assignment will be a task to familiarise yourself with basic text parsing, extraction, and manipulation. The assignment will use Python and will be a well-defined programming task. Artificial Intelligence (AI) and Machine Translation (MT) tools may be used for this assignment.
Note that all assignments are to be worked on individually and must be your own work except where the use of code written or provided by other entities (teaching staff, AI tools, etc.) is explicitly permitted by the assignment specification. Artificial Intelligence (AI) and Machine Translation (MT) tools are permitted to be used in the programming assignments in this course, but they are not required to be used and not recommended to be used as they may inhibit learning and introduce bugs into your code. You must always follow the referencing requirements set out in the assignment specification and documents referenced from the assignment specification. Failure to appropriately reference the resources (tools and information sources) used in your work may result in misconduct allegations against you. You are encouraged to discuss the concepts behind the assignments but under no circumstances should you show your code to, or allow your code to be seen by, another student. You should not look at the code of any other student. You must sufficiently protect all electronic and paper copies of your code. All submitted code will be subject to electronic plagiarism and collusion detection. Assignments with no academic merit will be awarded a mark of zero. You may have to verbally answer questions about your submission as part of the assignment marking process.
Submission guidelines
To be submitted online in Blackboard.
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.
Marked assignments with feedback and/or detailed solutions with feedback will be released to students within 14-21 days, where the earlier time frame applies if there are no extensions.
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.
Assignment 2
- Mode
- Product/ Artefact/ Multimedia, Written
- Category
- Computer Code, Paper/ Report/ Annotation
- Weight
- 25%
- Due date
24/10/2025 3:00 pm
- Learning outcomes
- L02, L03, L04, L05, L06
Task description
This will be a more open ended and challenging task that will draw on what you have learned this semester. The student will be expected to conduct a comparative analysis of several state-of-the-art solutions to a "hot topic" in NLP using a large dataset. The analysis will be written up in a 5-page report using a template that will be provided when the assignment is released. The report should include a detailed comparative analysis of the algorithms used, a clear and concise description of each algorithm, and include tables and graphs summarising the experiments ran. The datasets and necessary GPU hardware will be provided by the course coordinator, along with a description of the task, including at least one example baseline algorithm.
Artificial Intelligence (AI) and Machine Translation (MT) tools may be used for this assignment.
Note that all assignments are to be worked on individually and must be your own work except where the use of code written or provided by other entities (teaching staff, AI tools, etc.) is explicitly permitted by the assignment specification. Artificial Intelligence (AI) and Machine Translation (MT) tools are permitted to be used in the programming assignments in this course, but they are not required to be used and not recommended to be used as they may inhibit learning and introduce bugs into your code. You must always follow the referencing requirements set out in the assignment specification and documents referenced from the assignment specification. Failure to appropriately reference the resources (tools and information sources) used in your work may result in misconduct allegations against you. You are encouraged to discuss the concepts behind the assignments but under no circumstances should you show your code to, or allow your code to be seen by, another student. You should not look at the code of any other student. You must sufficiently protect all electronic and paper copies of your code. All submitted code will be subject to electronic plagiarism and collusion detection. Assignments with no academic merit will be awarded a mark of zero. You may have to verbally answer questions about your submission as part of the assignment marking process.
Submission guidelines
The report as well as the code to reproduce all of the results will be submitted as a zip file in Blackboard.
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.
Marked assignments with feedback and/or detailed solutions with feedback will be released to students within 14-21 days, where the earlier time frame applies if there are no extensions.
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 Exam
- Hurdle
- Identity Verified
- In-person
- Mode
- Written
- Category
- Examination
- Weight
- 50%
- Due date
End of Semester Exam Period
8/11/2025 - 22/11/2025
- Other conditions
- Time limited, Secure.
- Learning outcomes
- L01, L02, L03, L06
Task description
The final exam will be a 3-hour invigilated exam covering the concepts learned in the course.
Hurdle requirements
To pass this course, a minimum of 50% must be obtained in the final exam. If you achieve less than 50% in the final examination, your overall final mark will be capped at 49, and your final grade will be capped at 3.Exam details
| Planning time | 10 minutes |
|---|---|
| Duration | 180 minutes |
| Calculator options | (In person) Casio FX82 series only or UQ approved and labelled calculator |
| Open/closed book | Closed book examination - no written materials permitted |
| Materials | pen, pencil, eraser, ruler |
| Exam platform | Paper based |
| Invigilation | Invigilated in person |
Submission guidelines
Deferral or extension
You may be able to defer this exam.
Course grading
Full criteria for each grade is available in the Assessment Procedure.
| Grade | Cut off Marks | Description |
|---|---|---|
| 1 (Low Fail) | 0 - 19 |
Absence of evidence of achievement of course learning outcomes. |
| 2 (Fail) | 20 - 46 |
Minimal evidence of achievement of course learning outcomes. |
| 3 (Marginal Fail) | 47 - 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. |
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.
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 |
Lecture |
Lectures Learning outcomes: L01, L03 |
Multiple weeks From Week 2 To Week 13 |
Practical |
Practicals Weekly practicals starting in Week 2. Learning outcomes: L02, L04, 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
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: