Steven Bird
-
Research
Over the past thirty years, Steven Bird has been working with minoritised people groups in Africa, Melanesia, Amazonia, and Australia, and exploring how people keep their oral languages and cultures strong. He has held academic appointments at Edinburgh, UPenn, Berkeley, and Melbourne. Steven established the ACL Anthology, the Open Language Archives Community, and the Natural Language Toolkit, and is past president of the Association for Computational Linguistics. Since 2017 he has been research professor in the Northern Institute at Charles Darwin University, where he collaborates with Indigenous leaders and directs the Top End Language Lab. Steven pursues other language-related projects at http://aikuma.org.
-
Publications
Must NLP be extractive?, S Bird (2024), Proc 62nd ACL. 🏆
Envisioning NLP for intercultural climate communication, S Bird, A Aquino, I Gumbula (2024), Proc 1st Workshop on NLP Meets Climate Change.
Centering the speech community, S Bird, D Yibarbuk (2024), Proc 18th EACL. 🏆
Understanding how language revitalisation works: a realist synthesis, B Wiltshire, S Bird, R Hardwick (2022), Journal of Multilingual and Multicultural Development, 1–17.
"We are reconciliators": When Indigenous tourism begins with agency, N Curtin, S Bird (2022), Journal of Sustainable Tourism, 30, 461–481.
Sparse transcription, S Bird (2020), Computational Linguistics, 46, 713–744
-
Highlights
• Keynote Presentation CLARIN 2024
• Natural Language Processing with Python (O’Reilly, 2009)
• Petit Dictionnaire Yémba-Français (SIL Cameroon, 1997)
• Computational Phonology (Cambridge, 1995)
Learning English and Aboriginal Languages for Work
This project leverages mobile technologies to expand and enrich the communication between Indigenous and non-Indigenous Australians working together on Aboriginal owned or controlled country. We are generating new knowledge in the areas of oral language learning and on-country technology design, through extensive collaboration with Indigenous participants in Arnhem Land. Project outcomes include mobile technologies that support learning of spoken English and Aboriginal languages, new ways for Indigenous and non-Indigenous Australians to come together to design digital technologies and to learn each other's languages. (ARC DP19)
First Nations Climate Communication
This project is co-designing cross-cultural communications about weather using AI by partnering with Aboriginal communities in the Northern Territory, the Bureau of Meteorology and industry engineers. The project will build Aboriginal capacity in AI, and indigenous knowledge will improve the scientific accuracy of predictions and the outcomes of adaptation strategies. Culturally sensitive AI promises to have many benefits for Australia: improving crisis communications, limiting fatalities and injuries, and reducing the costs of emergency response, healthcare, trauma and damage to property and economic activity. (ARC DP24)
Investing in Aboriginal Languages
We are developing a systematic account of Aboriginal language programs and what makes them effective and sustainable. The project is creating an evidence base, leading to models of language revitalisation and how they work in each place, and for whom. The models show ways for local and national organisations to invest in Aboriginal languages, and what kinds of returns they can expect. The project involves a two-way collaboration with Aboriginal people across the country that will elevate local voices and build local capacity for designing and evaluating programs, businesses and technologies for keeping Aboriginal languages strong. (ARC DP21)