Dr Anupiya’s profile
Deep learning enhances Natural Language Understanding (NLU) due to its capability of learning features directly from data, as well as learning from the dynamic nature of natural language. Furthermore, deep learning has been shown to outperform most of the other machine learning approaches for NLU. His thesis demonstrates that by integrating semantic knowledge and a knowledge base, enhanced meaning and deep learning models are generated that improve the capability of NLU.
Anupiya has published multiple research papers on the outcomes of his research. His papers introduced novel approaches for use in the areas of NLU. His model on Long Term Memory Network (LTM) has been published in the International Joint Conference Neural Networks and his work is currently applied in a Natural Language Processing tool kit (KotlinNLP).
The judges were particularly impressed that Anupiya was an Australian Postgraduate Research Intern at Woodside Energy – a program for Australia’s brightest research talent. Anupiya applied his research in natural language classification and dialog analysis in the industrial oil and gas context. This is a difficult application with little curated data. Anupiya was able to analyse their problem domain, then use his research to explore useful alternatives. This kick-started work towards practical solutions, and he worked to implement some of them. They were impressed with Anupiya’s breadth of knowledge in computational linguistics and his practical approach to navigating suitable solutions in the business context.
In addition to Anupiya’s work on his PhD he participated in many other research activities working as a research assistant. He worked on a project in biosecurity by developing deep-learning models to predict invasive and non-invasive insects. He also applied his developed deep learning model in predicting email traffic, which is an important part of planning resources in an organisation. He also participated in a mini hackathon organised by Western Power in 2018, where he was a joint winner in developing a deep-learning solution to predict the electricity consumption.
Anupiya’s exceptional work in his PhD allowed him to join Murdoch University as a postdoctoral research fellow, working on a government-funded translation grant in collaboration with PathWest.
Anupiya is an active member of IEEE, where he has been an interim President of the Murdoch University branch and has given talks at branch meetings. He volunteers as a reviewer for IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Knowledge based Systems and IEEE Transactions on Memetic Computing, which are the few of the most prominent journals in Anupiya’s research areas. He has also volunteered to review papers for International Conference on Neural Networks, International Joint Conference on Neural Networks, and International Conference on Digital Image Computing: Techniques and Applications.