Fairness in Natural Language Processing. Natural language processing (NLP) has achieved spectacular commercial successes in recent years, and has been deployed across an ever-increasing breadth of devices and application areas. At the same time, there has been stark evidence to indicate that naively-trained models amplify biases in training data, and perform inconsistently across text relating to different demographic groupings of individuals. This project aims to systematically quantify the ext ....Fairness in Natural Language Processing. Natural language processing (NLP) has achieved spectacular commercial successes in recent years, and has been deployed across an ever-increasing breadth of devices and application areas. At the same time, there has been stark evidence to indicate that naively-trained models amplify biases in training data, and perform inconsistently across text relating to different demographic groupings of individuals. This project aims to systematically quantify the extent of such biases, and develop models that are both more socially equitable, as well as less prone to expose private data in the learned representations. In doing so, it will make NLP more accessible to new populations of users, and remove socio-technological barriers to NLP uptake.Read moreRead less
Automated assessment of data quality in biological knowledge resources. This project aims to develop methods for identifying poor quality data in biological databases. Research in biomedicine is underpinned by massive databases of biological data. Data quality is largely managed through manual curation, but automated methods to assess quality are critically needed. This project expects to develop a suite of computational tools for assessing biological data quality, utilising an innovative approa ....Automated assessment of data quality in biological knowledge resources. This project aims to develop methods for identifying poor quality data in biological databases. Research in biomedicine is underpinned by massive databases of biological data. Data quality is largely managed through manual curation, but automated methods to assess quality are critically needed. This project expects to develop a suite of computational tools for assessing biological data quality, utilising an innovative approach based on network analysis of database record connectivity. These tools will enable quantifying data quality at scale. Researchers, evidence-based decision-makers in biomedicine, and the analytical or predictive tools that use this data will make more reliable inferences and decisions.Read moreRead less
Exploiting Context in Multilingual Understanding and Generation. Automatic translation technologies produce incoherent and incorrect outputs in critical areas, such as health, finance, and law. This is due to translating sentences independently, without regard to the global extra-sentential context and rich linguistic structures inherent in the wider document context. This project aims to exploit global linguistic structures, capitalising on recent advances in deep neural networks, in order to g ....Exploiting Context in Multilingual Understanding and Generation. Automatic translation technologies produce incoherent and incorrect outputs in critical areas, such as health, finance, and law. This is due to translating sentences independently, without regard to the global extra-sentential context and rich linguistic structures inherent in the wider document context. This project aims to exploit global linguistic structures, capitalising on recent advances in deep neural networks, in order to generate coherent and faithful text. Expected outcome include next-generation computational technologies for language understanding and generation. This should significantly benefit document-based language technologies and increase their applications in a range of cultural, industrial, and health settings.Read moreRead less
AI for Legal Problem Diagnosis in the Diverse Language of Australians. The number of Australians with unmet legal needs is estimated to be over four million people per year and growing, and free legal assistance is severely under-resourced. A bottleneck for free legal assistance providers is the determination of what (if any) specific legal needs the individual has, to which end this project proposes to develop AI models to semi-automate the process, with particular focus on fairness across user ....AI for Legal Problem Diagnosis in the Diverse Language of Australians. The number of Australians with unmet legal needs is estimated to be over four million people per year and growing, and free legal assistance is severely under-resourced. A bottleneck for free legal assistance providers is the determination of what (if any) specific legal needs the individual has, to which end this project proposes to develop AI models to semi-automate the process, with particular focus on fairness across users of all backgrounds, generalisation from small amounts of curated data, and dynamic interaction with the help-seeker. The project will help deliver legal assistance to some of the most vulnerable members of Australian society, and reinforce Australia's position as a world leader in AI for Law.Read moreRead less