ACL 2021 Test of Time Award

Dr. Jean Carletta has been awarded the 2021 Association for Computational Linguistics 25-year Test-of-Time paper award for Assessing Agreement on Classification Tasks: The Kappa Statistic, Computational Linguistics 22 (1), 1996. In this paper she intervened to correct a common but misleading statistical practice. As a result, her field began to require assessments of how variability in subjective analyses could bias the claims made for their results. Although her work was based on existing content analysis best practice in the humanities, the clarity of her expression led to the paper being used widely in teaching research methods to medical students as far afield as Beijing.
Jean is a Senior Research Fellow in the School of Computer Science. She is engaged in a wide portfolio of work that takes a systems level approach to improving the impact Scotland’s academic community has on national cyber security and resilience.

https://www.aclweb.org/portal/content/announcement-2021-acl-test-time-paper-award-0

Seminar – Phong Le, Amazon – 3rd March 2021

Can Language Models be Weak Annotators

We are happy to have Phong Le, from Amazon, talk on Teams on Wed 3 March at 12 noon on Teams.

Abstract

Deep language models e.g. BERT and GPT3 are the breakthrough in Natural Language Processing in the last 3 years. Being trained on massive raw text data, they capture useful priors for several tasks such as syntactic parsing, information extraction, and question answering. Moreover, they are capable of answering factual and commonsense cloze questions such as “Dante was born in _____”. In this talk, I will firstly give an overview about what language models “know”. I will then present our work on exploiting their knowledge as weak supervision for a specific task called relation classification.

Relation classification, the identification of a particular relation type between two entities in text, requires annotated data. Data annotation is either a manual process for supervised learning, or automated, using knowledge bases for distant learning. However, both methodologies are costly and time-consuming since they depend on intensive human labour for annotation or for knowledge base creation. Using language models as annotators, on the contrary, is very cheap but the annotation quality is low. We hence propose NoelA, an auto-encoder using a noisy channel, to improve the accuracy by learning from the low quality annotated data. NoelA outperforms BERT and a bootstrapping baseline on TACRED and reWIKI datasets.

Bio: I’m an applied scientist at Amazon Alexa. Before that, I was a tenure-track research fellow at the University of Manchester. I did a postdoc with Ivan Titov at the University of Edinburgh, and got a PhD from the University of Amsterdam under the supervision of (Jelle) Willem Zuidema. I’m interested in neural networks and deep learning. My current work is to employ them to solve natural language processing tasks such as entity linking, coreference resolution, and dependency parsing. I’m also interested in formal semantics, especially learning semantic parsing.

For more details, please visit my homepage https://sites.google.com/site/lephongxyz/

 

Please note the session will not be recorded, to preserve the like-for-like nature of physical seminars and also avoid any privacy/rights issues.

Event details

  • When: 3rd March 2021 12:00 - 3rd February 2021 13:00
  • Format: Seminar

PhD Scholarships in Computer Science

Scholarship Description
The School of Computer Science is offering the following scholarships for 3.5 years of study in our PhD programme. All UK/EU and International students are eligible:

• 6 fully funded scholarships consisting of tuition + stipend
• 6 additional tuition-only scholarships

This award is part-funded through the University’s new ‘handsels’ scheme.

Value of Award
• Tuition scholarships cover PhD fees irrespective of country of origin.
• Stipends are valued £15,285 per annum.

Eligibility Criteria
We are looking for highly motivated research students willing to be part of a diverse and supportive research community. Applicants must hold a BSc or MSc in Computer Science or related area appropriate for their proposed topic of study.
International applications are welcome. We especially encourage female applicants and underrepresented minorities to apply.

Application Deadline
22 January 2021 for scholarship eligibility. Late applications will be considered if funding allows.

How to Apply
Every PhD application indicating interest, if accepted, will automatically be considered for these scholarships; there is no need for a separate application.
The best way to win one of our scholarships is to make a strong PhD application. You are also encouraged to approach supervisors before formal submission to discuss your project ideas with them.
The School’s main groups are Artificial Intelligence and Symbolic Computation, Computer Systems and Networks, Human-Computer Interaction, and Programming Languages. It is highly recommended that applicants identify potential supervisors in their applications. A list of existing faculty and areas of research can be found at https://www.st-andrews.ac.uk/computer-science/prospective/pgr/supervisors/).
Full application instructions can be found at https://www.st-andrews.ac.uk/study/apply/postgraduate/research/.
Inquiries and questions may be directed to pg-admin-cs@st-andrews.ac.uk.

Seminar – Richard Connor – 5th November

The second school seminar on 5th November at 2pm, on Teams.  If you do not have the Teams link available please contact the organiser, Ian Gent.

Dimensionality Reduction in non-Euclidean Spaces
Richard Connor
Deep Learning (ie Convolutional Neural Networks) gives astoundingly good classification over many domains, notably images. Less well known, but perhaps more exciting, are similarity models that can be applied to their inner layers, where there lurk data representations that can give a much more generic notion of similarity. The problem is that these data representations are huge, and so searching a very large space for similar objects is inherently intractable.
If we treat the data as high-dimensional vectors in Euclidean space, then a wealth of approximation techniques is available, most notably dimensionality reduction which can give much smaller forms of the data within acceptable error bounds. However, this data is not inherently a Euclidean space, and there are better ways of measuring similarity using more sophisticated metrics.
The problem now is that existing dimensionality reduction techniques perform analysis over the coordinate space to achieve the size reduction. The more sophisticated metrics give only relative distances and are not amenable to analysis of the coordinates. In this talk, we show a novel technique which uses only the distances among whole objects to achieve a mapping into a low dimensional Euclidean space. As well as being applicable to non-Euclidean metrics, its performance over Euclidean spaces themselves is also interesting.
This is work in progress; anyone interested is more than welcome to collaborate!

Learning to Describe: A New Approach to Computer Vision Based Ancient Coin Analysis

The work on deep learning based understanding of ancient coins by Jessica Cooper, who is a Research Assistant and a part-time PhD student supervised by Oggie Arandjelovic and David Harrison has been chosen as a featured, “title story” article by the Journal Sci where it was published in a Special Issue Machine Learning and Vision for Cultural Heritage.

Zoë Nengite awarded Principal’s Medal

Congratulations to Zoë Nengite who has been awarded The Principal’s Medal in recognition of outstanding academic achievement and exceptional activities within the University and the wider St Andrews community. The Medal is awarded to students who have both excellent academic accomplishments and those who have inspired and supported their peers and who have often undertaken extensive advocacy work, which has improved life for many of their fellow students.

Zoë sent us a reflection on time spent studying in the School and a photo celebrating with Mum.

“I’m really sad that my time at St Andrews has come to an end. I will especially miss the School of Computer Science. We are such a close community of students and staff alike. I will even miss the Jack Cole labs, despite spending many hours with my head in my hands stuck on a problem gripping my mug of coffee. I always knew that help wasn’t too hard to find.

“Some of my best memories are from my time at St Andrews. Most of them spent with my closest friends who also studied Computer Science. Coming from London, I was apprehensive about St Andrews, but it quickly became a place I called home. I think even years from now, it will always be somewhere I call home.”

The award was announced during the virtual conferral of degrees in July. Zoë hopes to attend a rescheduled Class of 2020 Ceremony in the future where we look forward to celebrating with her in person.