Department of CS newsletter

Congratulations to Andrea - and many thanks to Sean

Many congratulations to Andrea who is stepping into the Discipline Head of Education (DHoE) role in the New Year. At this point I’d like to very much thank Sean for his (many) years of leadership in this and similar roles. Sean’s level-headedness has helped the department navigate a number of challenges in recent times and I’m sure you’ll all join me in thanking Sean for his commitment and leadership. I am in no doubt that Andrea will be equally wonderful as our new DHoE.

23/24 Atlas and Inaugural Talk Seminar Series

Our 23/24 research seminar series features a number of talks by external speakers and by recently hired/promoted colleagues in the department. Each seminar will be followed by a social event - please do try to attend as many as you can as these are a good way to meet new (and not-so-new) colleagues. Titles and abstracts will be added to the schedule ahead of each talk. You can find the full list of seminars here.

Welcome to Stian Soiland-Reyes

Welcome to Stian Soiland-Reyes who has been appointed Senior Lecturer in FAIR, Open and Reproducible Digital Research. Stian’s research focuses on how researchers across domains can better share computational methods, complex data structures and structured metadata, with provenance of scientific activities, forming scholarly outputs of Research Objects in order to support Open Research.

Stian has helped build international communities and standard initiatives to formalize such FAIR digital objects using Linked Data, Web standards and computational workflow systems. He is promoting and supporting Open Research practices in networks including ELIXIR Europe and Research Data Alliance (RDA). Stian joined Computer Science in 2006 as a Research Associate and effectively Research Software Engineer (before that title existed!), and has since contributed to more than 14 international and national research projects on these topics. He has been teaching on the MSc Data Science programme since 2019. Stian will be co-leading the eScience Lab in the Information Management Group together with Carole Goble. The research group is currently active on 18 funded projects.

The S3 Group are in a Festive Mood

As you can see in the photo below, the Systems and Software Security (S3) Research Group are first off the festive mark with their recent group Christmas lunch at Habas.

Pete Jinks has passed away

Pete Jinks, who was in our department for many years until his retirement in 2012, has sadly passed away. I know many colleagues have fond memories of Pete. His son-in-law, David Lewis, has contacted me with funeral details: The funeral has been arranged for 1.30pm on Saturday the 9th of December in Fishguard. It's being held at the Chapel of Rest at the premises of Paul Jenkins and Sons, Feidir Castell, Fishguard SA65 9BD. Tel 01348 873250. Following the service all will be welcome at the wake at Cranged, St Nicholas, Goodwick SA64 0LX. Any queries please call David on 07733 223 232.

Andrew

The Department has created a new LinkedIn page, so please follow!

The Natural Language Processing and Text Mining team had 12 papers accepted this year at EMNLP2023 and EMNLP Findings. Well done to our PhD students and supervisors.

Boyang Liu, Viktor Schlegel, Riza Batista-Navarro and Sophia Ananiadou. "Argument mining as a multi-hop generative machine reading comprehension task" (EMNLP Findings)

Tharindu Madusanka, Iqra Zahid, Hao Li, Ian Pratt-Hartmann and Riza Batista-Navarro. "Not all quantifiers are equal: Probing Transformer-based language models' understanding of generalised quantifiers" (EMNLP)

Sarah Alsayyahi and Riza Batista-Navarro. "TIMELINE: Exhaustive Annotation of Temporal Relations Supporting the Automatic Ordering of Events in News Articles" (EMNLP)

Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang and Sophia Ananiadou. “Towards Interpretable Mental Health Analysis with Large Language Models” (EMNLP)

Li Y., Dong B., Guerin F. and Lin C. Compressing Context to Enhance Inference Efficiency of Large Language Models, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

Tang C., Shun S., Goldsack T. and Lin C. Improving Biomedical Abstractive Summarisation with Knowledge Aggregation from Citation Papers, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

Goldsack T., Zhang Z., Tang C., Scarton C. and Lin C. Enhancing Biomedical Lay Summarisation with External Knowledge Graphs, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

Jiang W., Mao Q., Lin C., Li J., Yang W., Deng T. and Wang Z. DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

Xiao C., Li Y., Hudson G., Lin C. and Moubayed N.  Length is a Curse and also a Blessing for Document-level Semantics, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

Loakman T., Maladry A. and Lin C. The Iron(ic) Melting Pot: Reviewing Human Evaluation in Humour, Irony and Sarcasm Generation, Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2023.

Bai J., Zhang X., Li C., Hong H., Xu X., Lin C. and Rong W. How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey, Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2023.

Liu J., Mao Q., Lin C., Song Y. and Li J. LATENTLOGIC: Learning Logic Rules in Latent Space over Knowledge Graphs, Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2023.

Co-located Workshops

Yulong W, Viktor Schlegel, Daniel Beck and Riza Batista-Navarro. "MMT’s Submission for the WMT 2023 Quality Estimation Shared Task". The Eighth Conference on Machine Translation (WMT 2023).

Abdullah Khered, Ingy Yasser Abdelhalim, Nadine Abdelhalim, Ahmed Soliman and Riza Batista-Navarro. "UniManc at NADI 2023 Shared Task: A Comparison of Various T5-based Models for Translating Arabic Dialectal Text to Modern Standard Arabic". The First Arabic Natural Language Processing Conference (ArabicNLP 2023).

Speaker Dr. Ernesto Jimenez-Ruiz

Location: Kilburn 1.3, 2pm start

Abstract:

The Ontology Matching community has been very active since the first steps of the Semantic Web. The Ontology Alignment Evaluation Initiative (OAEI) has been running annually since 2004. The objective of the OAEI is to perform a systematic evaluation of ontology matching systems to conduct a comparison on the same basis and to enable the reproducibility of the results. The OAEI includes several tracks of different nature and in a diverse set of domains, each of them including one or more matching tasks. Despite the amazing evaluation and system development efforts around the Ontology Matching community, there are still several challenges that need to be tackled from both the evaluation and system sides: (i) better connection with real-world needs and user involvement/satisfaction, (ii) discovery of mappings beyond atomic subsumption and equivalence, (iii) combination with machine learning methods, and (iv) awareness of the logical compatibility of the ontologies. In the presentation I will give an overview of the OAEI and the above challenges with a special focus on challenges (iii) and (iv), i.e., the two DLs (Deep Learning and Description Logics). While Deep Learning techniques are introducing elegant solutions with impressive results, the Ontology Matching community should not forget about the need of computing alignment sets that preserve the logical consistency (possibly with only intended entailments) of the integrated ontology (assuming that the alignment is interpreted as a set of Description Logic axioms).

Bio:

Dr. Ernesto Jimenez-Ruiz is a Lecturer in Artificial Intelligence (AI) and Senior Tutor for Research at City, University of London affiliated to the Adaptive Computer Systems and Machine Learning group. He is also one of the chairs of the Alan Turing Institute Interest Group on Knowledge Graphs. He previously held a Senior Research Associate position at The Alan Turing Institute in London (UK), a Research Assistant position at the University of Oxford and a part-time research position in the Centre for Scalable Data Access (SIRIUS) at the University of Oslo, Norway. His home university (Universitat Jaume I, Castellon, Spain) awarded a “Premio extraordinario de doctorado” (roughly translated as a Extraordinary Doctoral Award) to his doctoral thesis (Engineering category 2010-2011) for my research conducted within the Temporal Knowledge Bases Group. His research, over the past 15 years, has covered several areas within AI. Currently, he focuses on the intersection between Knowledge Representation (e.g., Knowledge Graphs) and Machine Learning with a special interest in creating more reliable and robust AI solutions. Knowledge graphs play a key role in AI and Data Science to enhance data-driven techniques with, among others, context and explainability.

Just a reminder to pop the Christmas do date in your diary:

Wed 20 Dec from 3.30pm in the Staff & PGR common room

Fun, Music, Pizza & Refreshments!

This week Professor Angelo Cangelosi's comments on humanoid robots were featured in the Daily Mail.

Deadline: 13-Dec-23

Accelerated Knowledge Transfer (AKT) is jointly delivered by Innovate UK and Innovate UK KTN and has been designed to create short-term (2-4 months) collaborations between a Business Partner or charity, and a UK Knowledge Base to rapidly inject innovation capacity in the UK. Inspired by KTP (Knowledge Transfer Partnership), AKT’s concept is to deliver a rapid and targeted intervention to accelerate the evaluation or development of an innovation project or concept, which has the potential for significant impact for the Business Partner.

The maximum grant is £35k per project and the Business Partner must contribute 10% (minimum) of the total project costs in cash.

Applications are facilitated via the KE Partnerships team, please contact kepartnerships@manchester.ac.uk

Deadline: no closing date
https://www.ukri.org/opportunity/mathematical-sciences-small-grants/

Applications to the Mathematical Sciences Small Grants funding opportunity must focus on original research projects or feasibility research studies. The majority of the research must be within the remit of the EPSRC Mathematical sciences theme and last up to 12 months (up to £100k).

Core application questions and assessment criteria will be used. Full applications can be submitted at any time and will be considered by EPSRC on a rolling basis. Standard EPSRC eligibility rules apply.

We have had several sightings of mice in Kilburn - these have been reported and pest control have attended.

Please remember to keep all food in sealed plastic containers and dispose of all food in either the kitchen green bins or rubbish bins in the corridors.  Do not keep food in pedestal drawers unless in a sealed container including sugar for tea/coffee.  Our furry friends will find anything not sealed up - so please check your own and shared areas.  Your help with this matter is much appreciated!