Skip to main content

A multi-label learning classifier on text data

Primary supervisor

Wray Buntine

Co-supervisors


Multi-label classification (MLC), which simultaneously assigns several labels to each instance, is critical in a wide variety of domains. One of the most difficult is a subset of data categorisation in which classes are arranged hierarchically and objects can be allocated to many paths of the class hierarchy concurrently. This is referred to as hierarchical multi-label classification (HMC), and it is useful for text classification. For example, the output of a news article may cover a variety of topics, including news, finance, and sports.

Student cohort

Single Semester
Double Semester

Aim/outline

The project's objective is to develop an MLC for a smaller two-level HMC model for classifying various patient cases in the medical field, although other text data could be used in this research.  In previous works, we investigated this issue by classifying the hierarchical data structure using the BERT transformer. The student will contribute to the development of the MLC algorithm and create a new model based on MLC to solve the domain task.

URLs/references

https://arxiv.org/pdf/2011.11197.pdf
https://ieeexplore.ieee.org/document/647171

Required knowledge

Practical knowledge of using modern deep learning methods as well as extensive experience with Python programming.

Standard Machine Learning, Artificial Intelligence and Natural Language Processing as covered in masters or advanced undergraduate subjects.

Good understanding of Machine Learning principles.