FIT5217 · Natural language processing

Overview

Natural language processing (NLP) stands as a cornerstone in the information age, made even more riveting with the rise of Generative AI and the introduction of models like LLM. NLP not only supports artificial intelligence in grasping intricate language nuances but also heralds a range of innovative applications. This unit delves into the fundamental principles of NLP, covering essential techniques for analyzing language syntax and meaning. We will also explore the neural network underpinnings of contemporary language models in the context of important real-world problems such as Machine Translation. Furthermore, we'll delve into the theoretical and practical foundations of recent LLMs.

Offerings

Assessment

The Handbook lists an examination for this unit.

This unit has threshold mark hurdles. You must achieve at least 45% of the available marks in the final scheduled assessment, at least 45% in total for in-semester assessments, and an overall unit mark of 50% or more to be able to pass the unit. If you do not achieve the threshold mark, you will receive a fail grade (NH) and a maximum mark of 45 for the unit.

Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.

Requisites

Learning outcomes

1. organise core problems and applications in NLP;
2. design systems to tackle NLP problems;
3. Evaluation of NLP models from utility & ethics, and safety perspectives.
4. assess various recent approaches to NLP.

Workload

Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled teaching activities. Clayton campus - no Lab in week 1.

Student experience, not official rules. Nothing here changes what the Handbook says.