University of Technology Sydney

42173 Advanced Natural Language Processing

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.

UTS: Information Technology: Computer Science
Credit points: 6 cp

Subject level:

Postgraduate

Result type: Grade and marks

Requisite(s): 42850 Natural Language Processing Algorithms

Description

Natural language processing is at the heart of many computing applications, such as voice-command systems, from major IT companies. This subject introduces advanced topics and technologies in natural language processing, and their applications to real-world problems. The subject builds on the previous NLP subject to give a deep understanding on how more powerful NLP algorithms work. It also introduces deep learning-based approaches that underpin the most currently advanced NLP technologies.

Subject learning objectives (SLOs)

Upon successful completion of this subject students should be able to:

1. Demonstrate an understanding of the advantages and limitations of several advanced natural language processing methods. (D.1)
2. Review technologies used in advanced natural language processing literature, and perform self-reflection. (F.1)
3. Develop an advanced natural language processing project for a real-world problem. (C.1)
4. Communicate project results in both oral and written forms. (E.1)

Course intended learning outcomes (CILOs)

This subject also contributes specifically to the development of the following Course Intended Learning Outcomes (CILOs):

  • 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

The subject is delivered by online learning material, lectures, and guest lectures. The lectures will provide students with advanced theories and practises in Advanced NLP. The guest lectures will feature current research frontline outcomes, as well as industry and business practises.

Content (topics)

  • Overview of natural language processing (NL)
  • Deep Neural Networks for NLP
  • Convolutional Neural Networks for NLP
  • Recurrent Neural Networks for NLP
  • Advanced Text Summarisation
  • Advanced Neural Translation
  • Recommender Systems
  • Web Analytics

Assessment

Assessment task 1: Quiz

Intent:

To demonstrate a clear understanding of the basic theories and algorithms underlying advanced NLP methods

Objective(s):

This assessment task addresses the following subject learning objectives (SLOs):

1

This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs):

D.1

Type: Quiz/test
Groupwork: Individual
Weight: 30%
Length:

2 hours

Assessment task 2: Literature review and reflection

Intent:

To ensure students can think critically about how advanced NLP technologies are developed in the current state-of-the-art literature.

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):

D.1 and F.1

Type: Report
Groupwork: Individual
Weight: 20%
Length:

The report will be 1,500 – 2,500 words in an 11-point font.

Assessment task 3: Research project development

Intent:

To apply advanced NLP methods to solve a practical real-world problem.

Objective(s):

This assessment task addresses the following subject learning objectives (SLOs):

1, 3 and 4

This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs):

C.1, D.1 and E.1

Type: Project
Groupwork: Group, individually assessed
Weight: 50%
Length:

The report will be 2,500 – 3,500 words in an 11-point font, plus an oral presentation.

Minimum requirements

In order to pass the subject, a student must achieve an overall mark of 50% or more.

Recommended texts

Eisenstein J. Introduction to Natural Language Processing. MIT Press; October 2019. ISBN: 9780262042840.

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