+61 399196100 Monday-Friday, 8:30am-5pm (AEST)
Enquire

Applied Natural Language Processing

Unit code: NIT6003 | Study level: Postgraduate
Credit points
12
(One credit point is usually equivalent to one hour of study per week)
Location
City Campus
Footscray Park
VU Sydney
Prerequisites
NIT5150 - Advanced Object Oriented Programming
(Or equivalent to be determined by unit coordinator)
Overview
Enquire

Overview

This unit applies machine learning and deep learning techniques to obtain leading results on solving the problems of natural language processing (NLP). NLP is considered as a critical step to create effective communications and interactions between machines and human beings. Through these applications in NLP the students will learn about the basic concepts of NLP, methodologies to represent human natural language in machines, and the application of cutting-edge techniques to train machines to achieve human-like abilities to understand natural language in a more effective way. The students will learn how to use machines to comprehend text that are used in most AI systems.

Learning Outcomes

On successful completion of this unit, students will be able to:

  1. Critically review natural language processing (NLP) applications and developments;
  2. Disaggregate and appraise the components in a typical NLP application architecture;
  3. Investigate and apply knowledge discovery processes and associated models to complex NLP application scenarios;
  4. Analyse state-of-art NLP techniques and evaluate the performance using various datasets; and
  5. Extrapolate knowledge and skills to design and develop an NLP application to support sustainable innovation, understand the importance of human factors and ethical considerations and provide business solutions.

Assessment

For Melbourne campuses

Assessment type: Laboratory Work
|
Grade: 20%
Lab submission (2)
Assessment type: Project
|
Grade: 40%
Projects (2)
Assessment type: Case Study
|
Grade: 40%
In-class Problem Solving Case Study for a scenario based real world problem (concepts, modelling, programming and scenario analysis)

The final project is due in week 8 in the delivery block.
Project 1 – Apply various supervised machine learning techniques to analyse and predict the sentiment of the given benchmark dataset and evaluate their performance.
Project 2 - Build a Machine comprehension model for the given benchmark dataset that trains the machine to understand the human language.

Required reading

Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition
Jurafsky, D & Martin, JH (2020)| Stanford University.

As part of a course

This unit is studied as part of the following course(s):

Graduate Certificate in Artificial Intelligence
NTAI
Master of Applied Information Technology
NMIT

Refer to the course page for information on how to apply for the course. VU takes care to ensure the accuracy of this unit information, but reserves the right to change or withdraw courses offered at any time. Please check that unit information is current with the Student Contact Centre.

Search for units, majors & minors