Compass Annual Conference
We are delighted to announce the Annual Compass Conference 2024, which is taking place in Bristol at the MShed on 22 October.
This year our theme will be “The Future of Data Science,” and we’d like to take the opportunity to celebrate the graduation of our first cohort of students, showcase the work of current students and consider questions on the future of data science – particularly in the context of artificial intelligence.
Respond to your invitation here: Compass Conference 2024 Late Registration form.
Late registration ends on 20 October.
We are excited to announce our keynote speaker: Prof Aline Villavicencio. She is the Director of the Institute of Data Science and Artificial Intelligence, University of Exeter, an affiliated member of the Department of Computer Science at the University of Sheffield (UK), and a fellow of the Alan Turing Institute. Her research on Natural Language Processing includes design and evaluation of (large) language models, multilinguality, idiomatic and figurative language and cognitively motivated natural language processing.
Our confirmed schedule is:
|
09:30 |
Registration and Welcome refreshments |
|
10:00 |
Introduction from the Director of Compass CDT |
|
10:15 |
Student research talks Rahil Morjaria - Group Testing Kieran James Morris - A trip to Bregman Geometry, and applications Ettore Fincato - Gradient-free optimization via integration Edward Milsom - Data modalities and the bias-variance decomposition |
|
11:15 |
Break |
|
11:30 |
Student lightning talks Cecina Babich Morrow - Bayesian Decision Analysis: A crash course. Sherman Khoo - Tensors and tensor manipulations in machine learning Rachel Wood - What is an anomaly in a network? Samuel Perren - Challenges in Decision-Making for Healthcare Treatments: Disconnected Networks and Single-Arm Studies Emma Tarmey - Making Music with Math: The Basics Sam Bowyer - How YOU – yes, YOU! – can train an LLM Henry Bourne - What’s Not in ‘The Future of Data Science’ Ben Anson - Self-supervised learning hyperparameter optimization with Bayes Josh Givens - A Quantile Alternative to the Conditional Average Treatment Effect (CATE) Hannah Sansford - Detecting Hallucinations in LLM outputs |
|
12:30 |
Lunch & poster session |
|
14:15 |
Panel presentations and discussion "Our data science journeys" Compass alumni Dominic Owens, Jake Spiteri, and Michael Whitehouse will be sharing insights about their journeys since graduating from the Compass programme. Followed by a discussion about what the future of data science might look like for Compass graduates. |
|
15:30 |
Break |
|
16:00 |
Keynote by Prof Aline Villavicencio, Director of the Institute for Data Science and Artificial Intelligence, University of Exeter (UK) Testing the Idiomatic Language Limits of Foundation Models: The strange case of the idiomatic eager beaver in cloud nine |
|
17:00 |
Closing remarks |
The School of Mathematics also hosts an AI research hub: INFORMED AI (https://www.informed-ai.net/). The Hub will hold an event for academic and industry partners on Monday 21 October. This will be an opportunity to find out about the research planned for the 5 year Hub project, meet the current partners and express an interest in future collaborations on the project. For more information about the Launch event, please see: https://www.informed-ai.net/events/.
Keynote: Testing the Idiomatic Language Limits of Foundation Models: The strange case of the idiomatic eager beaver in cloud nine
Aline Villavicencio (she/her)
Director of the Institute for Data Science and Artificial Intelligence, University of Exeter (UK)
Abstract
Large language models have been successfully used for capturing distinct (and very specific) word usages, and therefore could provide an attractive alternative for accurately determining meaning in language. However, these models still face a serious challenge when dealing with non-literal language, like that involved in Multiword Expressions (MWEs) such as idioms (make ends meet), light verb constructions (give a sigh), verb particle constructions (shake up) and noun compounds (loan shark). MWEs are an integral part of the mental lexicon of native speakers often used to express complex ideas in a simple and conventionalised way accepted by a given linguistic community. Although they may display a wealth of idiosyncrasies, from lexical, syntactic and semantic to statistical, that represents a real challenge for current NLP techniques, their accurate integration has the potential for improving the precision, naturalness and fluency of downstream tasks like machine translation. In this talk, I will present an overview of how advances in word representations have made an impact for the identification and modelling of idiomaticity and MWEs. I will concentrate on what models seem to incorporate of idiomaticity, as idiomatic interpretation may require knowledge that goes beyond what can be gathered from the individual words of an expression (e.g. “dark horse” as an unknown candidate who unexpectedly succeeds).
About the keynote speaker
Aline Villavicencio (she/her), Professor in Natural Language Processing, Director of the Institute for Data Science and Artificial Intelligence, University of Exeter (UK)
Aline Villavicencio is the Director of the Institute of Data Science and Artificial Intelligence, University of Exeter, affiliated to the Department of Computer Science, University of Sheffield (UK), and has a Fellowship at the Alan Turing Institute. Before these, she held academic positions in the Institute of Informatics, Federal University of Rio Grande do Sul, Brazil (between 2005 and 2021) and in the School of Computer Science and Electronic Engineering, University of Essex, UK.
She received her PhD from the University of Cambridge (UK), and held postdoc positions at the University of Cambridge and University of Essex (UK). She was a Visiting Scholar at the Massachusetts Institute of Technology (USA, 2011-2012 and 2014-2015), at the École Normale Supérieure (France, 2014), an Erasmus-Mundus Visting Scholar at Saarland University (Germany in 2012/2013) and at the University of Bath (UK, 2006-2009). She held a Research Fellowship from the Brazilian National Council for Scientific and Technological Development (Brazil, 2009-2017). She is a member of the editorial board of Computational Linguistics, TACL and of JNLE. She was the PC Co-Chair of the 60th Meeting of the Association for Computational Linguistics (ACL 2022), and was the PC chair of CoNLL-2019 and General co-chair for the 2018 International Conference on Computational Processing of Portuguese. She was also a member of the ELRA and NAACL boards, SIGLEX board and has co-chaired several events like workshops on Cognitive Aspects of Computational Language Acquisition and on Multiword Expressions. Her research on Natural Language Processing includes design and evaluation of (large) language models, multilinguality, idiomatic and figurative language and cognitively motivated NLP. She has co-edited special issues and books dedicated to these topics.
Past Conferences
Read more about the Compass Conference 2023 here.
Read about the previous edition of the Compass Conference in 2022 here.