Category Archives: news

Best Paper Award for Qur’an QA shared task 2022

RGCL is delighted to share that a team of our academics and PhD student have recently been awarded the Best Paper Award for Qur’an QA shared task 2022. This is at the 5th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT5) at the 13th Language Resources and Evaluation Conference (LREC 2022). This is the first best paper award for the recently established RIGHT Lab.

The organisers evaluated the papers based on different metrics:

Novelty of methods
Clear and good presentation of work
Released resources ( code etc )

photo of academic sat at a table in front of a screen with the presentation displayed

Authors: Damith Premasiri , Tharindu Ranasinghe , Wajdi Zaghouani , Ruslan Mitkov

Title: DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain

Abstract:

The task of machine reading comprehension (MRC) is a useful benchmark to evaluate the natural language understanding of machines. It has gained popularity in the natural language processing (NLP) field mainly due to the large number of datasets released for many languages. However, the research in MRC has been understudied in several domains, including religious texts. The goal of the Qur’an QA 2022 shared task is to fill this gap by producing state-of-the-art question answering and reading comprehension research on Qur’an. This paper describes the DTW entry to the Quran QA 2022 shared task. Our methodology uses transfer learning to take advantage of available Arabic MRC data. We further improve the results using various ensemble learning strategies. Our approach provided a partial Reciprocal Rank (pRR) score of 0.49 on the test set, proving its strong performance on the task.

Winners of the Vice-Chancellor’s Awards for Staff Excellence

Earlier this week the Vice-Chancellor’s Awards for Staff Excellence took place. Our Admin Team – April, Suman, Kate, Amanda and Emma – were nominated and won their category of ‘Excellence in partnerships’. If you were unable to join the event, you can watch it back on YouTube. The staff awards brochure can now also be viewed online, which includes an overview of all the shortlisted nominees.

Excellence in partnerships

“An individual or a team that has demonstrated outstanding commitment and professionalism through partnership working, to a high-quality service to our students, staff or stakeholders”.

Winners: RIILP Administrative Team: April Harper, Amanda Bloore, Suman Hira, Kate Wilson, Emma Franklin for supporting the institutional research trajectory by providing infrastructure, systems and processes as well as a positive attitude.

Congratulations Ladies!

EM TTI Application Portal now open!

Erasmus Mundus European Master’s in Technology for Translation and Interpreting (EM TTI)

Call for applications for start date September 2022

Scholarship application deadline: 15^th January 2022

Self-funded application deadline: 1^st July 2022

We invite applications for the new Erasmus Mundus European Master’s programme in Technology for Translation and Interpreting (EM TTI) with a start date of September 2022. The programme, run by University of Wolverhampton, University of Malaga, New Bulgarian University and Ghent University, offers students the opportunity to study at two international institutions and to undertake work placements with industry leaders around the world. A competitive Erasmus Mundus scholarship is offered to the highest-ranking applicants. Both European and non-European students can apply.

How to apply: https://em-tti.eu/how-to-apply

Course Fees: https://em-tti.eu/about-masters/course-fees/

Should you have any questions, please do not hesitate to contact the EM TTI team at enquiries@em-tti.eu.

Responsible Digital Humanities Lab (RIGHT) – Job Vacancies

The Responsible Digital Humanities Lab (RIGHT) is the first of its kind in the UK and seeks to be a regional, national, and international leader in the field of Digital Humanities (DH). RIGHT’s priorities will be to advance the field of DH, foster strong collaboration across the University of Wolverhampton (UoW), and create tools, datasets and guidelines for ethical, responsible Natural Language Programming (NLP) focused DH. The emphasis on responsible DH makes it a unique, pioneering hub for advancing human-centred computing. We bring AI to the Humanities while also utilising active research in the Humanities, which engages with questions of ethics and the human experience, to guide responsible progress in AI.

RIGHT will harness NLP, corpus-based and Deep Learning expertise to deliver internationally leading research in Humanities disciplines such as Sikh and Panjabi Studies, History, Literature and Film Studies with impact reaching far beyond academia. It will develop a flagship DH initiative for Panjabi with the Centre for Sikh and Panjabi Studies. RIGHT will be situated within the Research Group in Computational Linguistics (RGCL), which has a strong track record of NLP and DH research, prestigious national and International collaborations, and strong collaborative links within UoW. RIGHT will be supported by the Statistical Cybermetrics Research Group (SCRG) and the Centre for Sikh and Panjabi Studies.

There are 3 Lecturer posts and one Research Associate for which we are currently recruiting.

Panjabi Digital Accessibility and Literary Heritage Research Associate

RIGHT Lecturer in Computer Vision and Deep Learning for Digital Humanities

RIGHT Lecturer in Corpus-based Digital Humanities

RIGHT Lecturer in Natural Language Processing and Deep Learning for Digital Humanities

The University of Wolverhampton celebrates diversity and recognises that difference brings value to our organisation.

As part of our commitment to ensure the diversity of staff body reflects the diversity of the student and local communities we serve, we particularly welcome applications from candidates of Black, Asian, or Ethnic Minority heritage, and candidates who are Disabled (including people who whilst not self-defining as disabled do encounter challenges due to a society that disables them by lack of inclusivity).

We are proud to have been awarded Disability Confident employer status, included in the Stonewall list of employers and are working towards improving our practices against Athena Swan and the Race Equality Charter. We believe in creating an even playing field for all our colleagues, where we can all belong.

PLEASE NOTE: Applications are scored against the criteria set out in the job description and person specifications attached to this advert. Applications are not assessed against the job advert so please ensure your applications are crafted against the Job Description and Person Specification contained within it.

3 PhD studentships on NLP and DL approaches in Digital Humanities

Research Group in Computational Linguistics,

Research Institute of Information and Language Processing,

University of Wolverhampton

*** Closing date 19 July 2021 ***

The Research Group in Computational Linguistics (http://rgcl.wlv.ac.uk) at the Research Institute of Information and Language Processing of the University of Wolverhampton invites applications

for three PhD studentships with the prospective PhD students working on the following topics: (i) Natural Language Processing (NLP) and Deep Learning (DL) in Computational History studies, (ii) NLP and DL in Computational Literature studies and (iii) NLP and DL in Computational Film Studies.

These are 3-year funded bursaries which will include a stipend towards living expenses (£15,609 per year) with the tuition fees and the research fees included.

Applicants will submit PhD research proposals not exceeding 2,000 words. The applicants are invited to propose an original computational history study, computational literature study or computational film study where NLP and DL techniques are employed.

Prerequisites

A successful applicant must have a good honours degree or equivalent in Computer Science, Computational Linguistics, Digital Humanities or Linguistics, with good programming skills, and knowledge of Deep Learning and Natural Language Processing.

Application procedure

Applications must include:

Research proposal not exceeding 2,000 words (see above)
A curriculum vitae listing degrees awarded, courses covered and marks obtained, publications, relevant experience and names of two referees who could be contacted for a reference
Cover letter with statement of research interests, outlining why you are interested in this PhD position/topic, how you plan to approach the research task and why you consider your experience is relevant.

Schedule

The application deadline is 19 July 2021. The short-listed candidates will be notified by email by 20 July 2021 and interviewed via Zoom on 21 or 22 July 2021. The starting date of the PhD position is 1 September 2021 or any time as soon as possible after that.

Established by Prof Mitkov in 1998, the research group in Computational Linguistics delivers cutting-edge research in a number of NLP areas. The results from the UK research assessment exercises confirm the research group in Computational Linguistics as one of the top performers in UK and international research with its research assessed as ‘internationally leading, internationally excellent and internationally recognised’.

The PhD students will be members of the newly established Responsible Digital Humanities Research Lab which is part of the Research Group of Computational Linguistics.

Applications should be sent by email to

Prof Dr Ruslan Mitkov

Director of Research Institute of Information and Language Processing

University of Wolverhampton

Email: R.Mitkov@wlv.ac.uk

and copied to Prof Mitkov’s PAs Miss Suman Hira (suman.hira@wlv.ac.uk) and Mrs April Harper (a.harper2@wlv.ac.uk)

Papers accepted at ACL-IJCNLP 2021 and NAACL-HWT 2021

Congratulations to Dr Frédéric Blain who has had the following papers accepted at upcoming conferences.

Title: Knowledge Distillation for Quality Estimation

Authors: Amit Gajbhiye, Marina Fomicheva, Fernando Alva-Manchego, Frédéric Blain, Abiola Obamuyide, Nikolaos Aletras and Lucia Specia

Abstract: Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent success in QE stems from the use of multilingual pre-trained representations,where very large models lead to impressive results. However, the inference time, disk and memory requirements of such models do not allow for wide usage in the real world.

Attempts have been made at making pre-trained representations less resource-hungry by using knowledge distillation, but the resulting models remain prohibitively large for many usage scenarios.Instead of building upon distilled pre-trained representations, we propose to transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. In combination with a confidence-based data augmentation approach, we show that it is possible to create light-weight QE models that achieve comparable results to distilled pre-trained representations with 8x fewer parameters.

This paper should appear in the Findings of ACL-IJCNLP 2021 (https://2021.aclweb.org/).

Title: Backtranslation Feedback Improves User Confidence in MT, Not Quality

Authors: Vilém Zouhar, Michal Novák, Matúš Žilinec, Ondřej Bojar, Mateo Obregón, Robin L. Hill, Frédéric Blain, Marina Fomicheva, Lucia Specia, Lisa Yankovskaya

Abstract: Translating text into a language unknown to the text’s author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility. We demonstrate this by showing three ways in which user confidence in the outbound translation, as well as its overall final quality, can be affected: backward translation, quality estimation (with alignment) and source paraphrasing. In this paper, we describe an experiment on outbound translation from English to Czech and Estonian. We examine the effects of each proposed feedback module and further focus on how the quality of machine translation systems influence these findings and the user perception of success. We show that backward translation feedback has a mixed effect on the whole process: it increases user confidence in the produced translation, but not the objective quality.

This paper will appear at NAACL-HWT 2021 (https://2021.naacl.org/).

The paper can also be found here: https://arxiv.org/abs/2104.05688