42850 Natural Language Processing Algorithms
Warning: The information on this page is indicative. The subject outline for a
particular session, location and mode of offering is the authoritative source
of all information about the subject for that offering. Required texts, recommended texts and references in particular are likely to change. Students will be provided with a subject outline once they enrol in the subject.
Subject handbook information prior to 2025 is available in the Archives.
Credit points: 6 cp
Subject level:
Postgraduate
Result type: Grade and marksRequisite(s): 32130 Fundamentals of Data Analytics OR 48 credit points of completed study in spk(s): C04379 Master of Business Analytics (Extension)
Anti-requisite(s): 41043 Natural Language Processing
Description
Natural Language Processing (NLP) develops statistical techniques and algorithms to automatically process natural languages (such as English), which rely on a number of AI areas, such as, text understanding and summarisation, machine translation, and sentiment analysis. This subject introduces the foundations of technologies in NLP, the current state-of-the-art NLP algorithms, and their applications to practical problems. It brings together cutting-edge research with practical techniques in NLP, providing students with the knowledge and capacity to conduct NLP research and to develop NLP projects.
Subject learning objectives (SLOs)
Upon successful completion of this subject students should be able to:
| 1. | Identify NLP applications in business and social contexts. (B.1) |
|---|---|
| 2. | Reflect on their own NLP skill development. (F.1) |
| 3. | Explain the advantages and disadvantages of different NLP methods and algorithms and their applicability in different business situations. (D.1) |
| 4. | Design and implement solutions for real-world NLP problems. (C.1) |
| 5. | Interpret the results of an NLP project. (E.1) |
Course intended learning outcomes (CILOs)
This subject also contributes specifically to the development of the following Course Intended Learning Outcomes (CILOs):
- Socially Responsible: FEIT graduates identify, engage, and influence stakeholders, and apply expert judgment establishing and managing constraints, conflicts and uncertainties within a hazards and risk framework to define system requirements and interactivity. (B.1)
- Design Oriented: FEIT graduates apply problem solving, design thinking and decision-making methodologies in new contexts or to novel problems, to explore, test, analyse and synthesise complex ideas, theories or concepts. (C.1)
- Technically Proficient: FEIT graduates apply theoretical, conceptual, software and physical tools and advanced discipline knowledge to research, evaluate and predict future performance of systems characterised by complexity. (D.1)
- Collaborative and Communicative: FEIT graduates work as an effective member or leader of diverse teams, communicating effectively and operating autonomously within cross-disciplinary and cross-cultural contexts in the workplace. (E.1)
- Reflective: FEIT graduates critically self-review their own and others' performance with a high level of responsibility to improve and practice competently for the benefit of professional practice and society. (F.1)
Teaching and learning strategies
This subject includes combined workshop and laboratory sessions (2 hours) with research and development work for the assignments. The workshop/laboratory sessions will have both individual and group activities, covering NLP theories and algorithms, hands-on exercise on NLP tools, and the understanding and interpretation of NLP project results.
Students are encouraged to engage in pre-reading materials, which will be made available on Canvas, and come with prepared questions for the workshops. During the workshop activities, students will receive feedback from the teaching staff and their student peers in a collaborative and discursive learning context.
Content (topics)
- Text processing and word embedding vectors
- Part-of-speech tagging
- Language and topic modelling
- Sentiment Analysis
- Text Summarisation
- Machine Translation
Assessment
Assessment task 1: Industry and Society Understanding and Analysis
| Intent: | To understand the current industry and society needs with respect to NLP-related jobs and skills. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 1 and 2 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): B.1 and F.1 |
| Type: | Report |
| Groupwork: | Individual |
| Weight: | 20% |
| Length: | A report up to 1000 words, including references. |
Assessment task 2: Quiz
| Intent: | To undertake a quiz. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 3 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): D.1 |
| Type: | Quiz/test |
| Groupwork: | Individual |
| Weight: | 30% |
Assessment task 3: Project Development
| Intent: | To design and implement solutions for real-world NLP problems in a research project and interpret the results of their projects. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 4 and 5 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): C.1 and E.1 |
| Type: | Project |
| Groupwork: | Group, individually assessed |
| Weight: | 50% |
| Length: | A report up to 3500 words, including references, plus an oral defence. |
Minimum requirements
In order to pass the subject, a student must achieve an overall mark of 50% or more.
Required texts
Eisenstein J. Introduction to Natural Language Processing. MIT Press; October 2019. ISBN: 9780262042840.
Recommended texts
NLP tutorial: https://www.upf.edu/web/mtg/nlp-tutorial
Foundations of Statistical Natural Language Processing: https://nlp.stanford.edu/fsnlp
The structure of modern English: https://muse.jhu.edu/article/19425