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
Improving human reasoning with causal Bayes networks: a multimodal approach. This project aims to improve human causal and probabilistic reasoning about complex systems by taking a user-centric, multimodal, interactive approach. The project will explore new integrated visual and verbal ways of explaining a causal probabilistic model and its reasoning, to reduce known human reasoning difficulties, and investigate how to reduce cognitive load by prioritising the most useful user- and context-speci ....Improving human reasoning with causal Bayes networks: a multimodal approach. This project aims to improve human causal and probabilistic reasoning about complex systems by taking a user-centric, multimodal, interactive approach. The project will explore new integrated visual and verbal ways of explaining a causal probabilistic model and its reasoning, to reduce known human reasoning difficulties, and investigate how to reduce cognitive load by prioritising the most useful user- and context-specific information. Expected outcomes include novel AI methods that empower users to drive the reasoning process and strengthen trust in the system’s reasoning. Performance will be assessed in medical and legal domains, with significant potential benefits to end users from better, more transparent reasoning and decision making.Read moreRead less
Towards realistic verbal interactions between people and computers-a probabilistic approach. This project aims to facilitate natural spoken interactions between people and computer systems, addressing obstacles to the acceptance of these systems. We will investigate computational models for relevant aspects of spoken dialogue, which will be implemented in computer systems for diverse tasks (for example, home devices and phone-enabled services).
Explaining the outcomes of complex computational models. This project aims to develop new algorithms that automatically generate explanations for the results produced by complex computational models. In recent times, these models have become increasingly accurate, and hence pervasive. However, the reasoning of Deep Neural Networks and Bayesian Networks, and of complex Regression models and Decision Trees is often unclear, impairing effective decision making by practitioners who use the results o ....Explaining the outcomes of complex computational models. This project aims to develop new algorithms that automatically generate explanations for the results produced by complex computational models. In recent times, these models have become increasingly accurate, and hence pervasive. However, the reasoning of Deep Neural Networks and Bayesian Networks, and of complex Regression models and Decision Trees is often unclear, impairing effective decision making by practitioners who use the results of these models or investigate the decisions made by the systems. Practical benefits of clear decision making reasoning by complex computational models include reduced risk, increased productivity and revenue, appropriate adoption of technologies including improved education for practitioners, and improved outcomes for end users. Significant benefits will be demonstrated through the evaluations with practitioners in the areas of healthcare and energy.Read moreRead less
Language engineering in the field: preserving 100 endangered languages in New Guinea. Efforts to preserve the world's endangered linguistic heritage are labour-intensive, and unable to keep up with the pace of language loss. This project investigates a new approach to language preservation, using techniques from language engineering, and leveraging the labour of mother-tongue speakers.
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
An intelligent machine modelling assistant for combinatorial optimisation. This project aims to discover key fundamental technologies for automating assistance to non-expert users in the formulation of mathematical models. Through automating the modelling of combinatorial optimization problems, this research will generate new knowledge to address the fundamental challenges of automatic mathematical modelling. This intelligent assistant will enable synthesis of new mathematical models through th ....An intelligent machine modelling assistant for combinatorial optimisation. This project aims to discover key fundamental technologies for automating assistance to non-expert users in the formulation of mathematical models. Through automating the modelling of combinatorial optimization problems, this research will generate new knowledge to address the fundamental challenges of automatic mathematical modelling. This intelligent assistant will enable synthesis of new mathematical models through the utilisation of pioneering natural language processing components and novel custom-made machine-readable knowledge bases. The outcome of this research will broaden access to high-quality models by non-expert workforce and alleviate the shortage of expert mathematicians, bringing significant social and economic benefits.Read moreRead less
Natural language processing for automated validation of protein databases. The project aims to use natural language processing and information retrieval to reconcile and improve sources of biological information. Biological research has produced vast volumes of information about proteins, captured in structured resources (databases) and unstructured documents. However, the accuracy of much of this information is questionable. The project proposes to develop methods to validate data and reduce th ....Natural language processing for automated validation of protein databases. The project aims to use natural language processing and information retrieval to reconcile and improve sources of biological information. Biological research has produced vast volumes of information about proteins, captured in structured resources (databases) and unstructured documents. However, the accuracy of much of this information is questionable. The project proposes to develop methods to validate data and reduce the dramatic inconsistencies in protein information resources by leveraging observed correlations and complementarity between them, and specifically through targeted fact extraction from the biomedical literature. These methods will be applied at scale across millions of published articles, to infer and validate functional information.Read moreRead less
Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models ....Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models, based on the incorporation of an explicit searchable memory, which will dramatically reduce model size, hardware requirements and energy usage. This will make modern natural language processing more accessible, while also providing greater flexibility, allowing for more adaptable and portable technologies.Read moreRead less
Understanding political debate and policy decisions using big data. This project aims to empirically test a novel framework for analysing the relationship between political debates and policy decisions. Using digital sources and computational modelling approaches, it will investigate three specific issues to test this framework. These issues, all drawn from different policy sectors, will be examined as a series of debates linked to specific decisions, over the last two decades. The expected outc ....Understanding political debate and policy decisions using big data. This project aims to empirically test a novel framework for analysing the relationship between political debates and policy decisions. Using digital sources and computational modelling approaches, it will investigate three specific issues to test this framework. These issues, all drawn from different policy sectors, will be examined as a series of debates linked to specific decisions, over the last two decades. The expected outcomes will provide insights into links between political debates and policy decisions with potential benefits for politics and policy-making.Read moreRead less