Discovery Early Career Researcher Award - Grant ID: DE230100049
Funder
Australian Research Council
Funding Amount
$459,030.00
Summary
Towards automated Australian Sign Language translation. This project aims to address the computational modelling of Auslan. The project expects to generate knowledge by creating the largest Auslan dataset, enabling further advancements in this research area. The dataset will also play an essential role in other research fields, e.g., sign linguistics. Expected outcomes include the invention of the first Auslan recogniser and generator capable of distinguishing and synthesising 1000+ signs, repre ....Towards automated Australian Sign Language translation. This project aims to address the computational modelling of Auslan. The project expects to generate knowledge by creating the largest Auslan dataset, enabling further advancements in this research area. The dataset will also play an essential role in other research fields, e.g., sign linguistics. Expected outcomes include the invention of the first Auslan recogniser and generator capable of distinguishing and synthesising 1000+ signs, representing a substantial advancement towards fully automated Auslan translation. This should provide significant benefits for the Australian Deaf community, such as high-quality digital systems for education and communication, resulting in increased quality of life and inclusion in the Australian society.Read moreRead less
First Nations AI: Country, Climate, Communication. Our team of Indigenous and western scholars aims to develop a systematic account of artificial intelligence and its possibilities in climate change communication in remote First Nations communities in northern Australia. Working under Indigenous governance, we will establish spaces for Indigenous landowners and scientists to come together to probe diverse AI techniques for making sense of climate predictions and risks. We will build the capacity ....First Nations AI: Country, Climate, Communication. Our team of Indigenous and western scholars aims to develop a systematic account of artificial intelligence and its possibilities in climate change communication in remote First Nations communities in northern Australia. Working under Indigenous governance, we will establish spaces for Indigenous landowners and scientists to come together to probe diverse AI techniques for making sense of climate predictions and risks. We will build the capacity of Indigenous people to conceive and design AI, accounting for divergent languages and knowledge systems. This is expected to lead to more effective and trustworthy communications about extreme weather and climate change, improving the preparedness and responses of remote First Nations communities.Read moreRead less
#thismymob: Digital land rights and reconnecting Indigenous communities. This project aims to investigate how social technology can connect Indigenous communities and enhance wellbeing; design culturally appropriate and sensitive technologies that afford a safe refuge for Indigenous peoples and their communities. This project will design and evaluate a mobile app to implement a national-scale, Indigenous-led technology development project and develop a national technology research and developmen ....#thismymob: Digital land rights and reconnecting Indigenous communities. This project aims to investigate how social technology can connect Indigenous communities and enhance wellbeing; design culturally appropriate and sensitive technologies that afford a safe refuge for Indigenous peoples and their communities. This project will design and evaluate a mobile app to implement a national-scale, Indigenous-led technology development project and develop a national technology research and development framework and post-secondary Indigenous software engineering curricula. The project expects to benefit Indigenous developers, entrepreneurs and start-ups to develop, operate and own technology.Read moreRead less
Architectural Design Across Spaces and Cultures: Technology and Language. This project addresses two significant productivity barriers facing Australia’s architectural practices; designing in spatially distributed and culturally diverse teams.
While design practices are central to sustaining Australia’s creative export sector, growing concerns associated with online, multilingual design teams have been identified.
Directly responding to Australia’s COVID-19 recovery plans, this research seeks ....Architectural Design Across Spaces and Cultures: Technology and Language. This project addresses two significant productivity barriers facing Australia’s architectural practices; designing in spatially distributed and culturally diverse teams.
While design practices are central to sustaining Australia’s creative export sector, growing concerns associated with online, multilingual design teams have been identified.
Directly responding to Australia’s COVID-19 recovery plans, this research seeks to develop new knowledge about the cognitive, social and technical factors that shape the effectiveness of online international design teamwork. Its goal is to leverage the opportunities provided through technological advances and multicultural practices, to remove barriers to design productivity and enhance creativity.Read moreRead less
Learning Deep Semantics for Automatic Translation between Human Languages. This project seeks to integrate deep linguistics and deep learning to improve translation quality. The modern world relies increasingly on automatic translation of human languages to deal with billions of documents. Current translation systems struggle with complex texts and often produce misleading or incoherent outputs. Furthermore, they translate sentences independently and ignore their overall document-wide context. T ....Learning Deep Semantics for Automatic Translation between Human Languages. This project seeks to integrate deep linguistics and deep learning to improve translation quality. The modern world relies increasingly on automatic translation of human languages to deal with billions of documents. Current translation systems struggle with complex texts and often produce misleading or incoherent outputs. Furthermore, they translate sentences independently and ignore their overall document-wide context. This project seeks to address these issues by developing a new approach using semantics – the underlying meaning of the text – to drive translation, both as discrete structures and continuous representations learned via deep learning. This may improve translation quality, thereby improving automatic translation for end-users.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
Adaptive Context-Dependent Machine Translation for Heterogeneous Text. While automatic machine translation technologies are undoubtedly useful to a wide range of users, they often produce incoherent outputs for many types of input, for example, medical, literature, or even conversational text. This project will develop new adaptive machine translation systems to handle many domains and text styles, including heterogeneous mixed-domain inputs. It will develop multi-task machine learning methods f ....Adaptive Context-Dependent Machine Translation for Heterogeneous Text. While automatic machine translation technologies are undoubtedly useful to a wide range of users, they often produce incoherent outputs for many types of input, for example, medical, literature, or even conversational text. This project will develop new adaptive machine translation systems to handle many domains and text styles, including heterogeneous mixed-domain inputs. It will develop multi-task machine learning methods for training collections of domain-specific translation systems while leveraging correlations between domains. This approach will reduce the big data requirements of current translation systems, and improve translation quality across a wide range of different language pairs and application domains.Read moreRead less
Images, perceptions and resources: enhancing Australias role in China's English language education. Education, being the third largest export industry, plays an extremely important role in Australia's engagement with the Asia region. Chinese students are by far the largest single group of overseas students studying in Australia. However, there is little evidence regarding Australia's presence in the English language market in China, nor of how Chinese language learning businesses draw on Austral ....Images, perceptions and resources: enhancing Australias role in China's English language education. Education, being the third largest export industry, plays an extremely important role in Australia's engagement with the Asia region. Chinese students are by far the largest single group of overseas students studying in Australia. However, there is little evidence regarding Australia's presence in the English language market in China, nor of how Chinese language learning businesses draw on Australian sources and resources. The association with two premier Chinese language learning and publishing houses through this joint research project will promote Australian content for language learners in China and provide information for Australian language resource developers focusing on the Chinese market.Read moreRead less
ARC Centre of Excellence for the Dynamics of Language. Language is central to human existence and to the flow of information. The Centre will address the most critical questions about language: How do languages evolve? How different can languages be? How do our brains acquire and process them? How can technologies deal with the complexity and enormous variability of language in its central role in human information processing? What can Australia do to increase its linguistic abilities at a time ....ARC Centre of Excellence for the Dynamics of Language. Language is central to human existence and to the flow of information. The Centre will address the most critical questions about language: How do languages evolve? How different can languages be? How do our brains acquire and process them? How can technologies deal with the complexity and enormous variability of language in its central role in human information processing? What can Australia do to increase its linguistic abilities at a time of increasingly multilingual demands in trade and information? The Centre will also secure language heritage, develop new language technologies, connect policy with indigenous and migrant communities, and build strategies to help 1st and 2nd language learning and those isolated by language difficulties.Read moreRead less