2 Apr 2026
Job Information
- Organisation/Company
South East Technological University- Research Field
Computer science
Engineering
Mathematics- Researcher Profile
First Stage Researcher (R1)- Positions
PhD Positions- Application Deadline
22 Apr 2026 - 16:00 (Europe/Dublin)- Country
Ireland- Type of Contract
Other- Type of Contract Extra Information
N/A 4-year PhD scholarship- Job Status
Full-time- Hours Per Week
40- Is the job funded through the EU Research Framework Programme?
Not funded by a EU programme- Is the Job related to staff position within a Research Infrastructure?
No
Offer Description
Scholarship Project Title: Agentic Retrieval-Augmented Generation for Terminology Translation in Neural Machine Translation
Advert Reference number: SETU_2025_14_CW
Supervisors:
Dr Rejwanul Haque, Department of Computing, Faculty of Science, SETU Carlow, Carlow, Ireland.
Dr Souhail Bakkali, IRISA, ESIR, University of Rennes, France
Prof Antoine Doucet, L3i Laboratory, Computer Science Department, University of La Rochelle, France
Dr Joss Moorkens, ADAPT Centre, School of Applied Language & Intercultural Studies, Dublin City University, Ireland
Research Group: ADMIRE, Twin Transition Centre (TTC)
Department /School/Faculty: Department of Computer Science, Faculty of Science
Duration: 4 Years/48 Months
Status: Full-time / part-time: Full Time
Funding information: SETU 2025 Presidents Scholarship Programme
Value of the scholarship per year for four years:
- Stipend: €22,500 per annum
- Fees of €5,750 per annum
- Research costs- €2,000 per annum
Closing date and time: Wednesday, 22 April at 4pm Irish time
Interview date: To be confirmed
PhD commencement date: To be confirmed
Project Key Words: Machine Translation, Natural Language Processing, Terminology Translation, Agentic RAG
Post summary
We are looking for a candidate for a fully-funded PhD position on the topic of Terminology Translation in Neural Machine Translation
Domain terms are productive in nature, and their translations are dealt with priority in any translation workflows (TWs). Translation service providers (TSPs) who use machine translation (MT) in their translation pipeline expect terminology translation to be unambiguous and consistent with the context and domain in question. Although the current state-of-the-art neural MT (NMT) models are capable of producing high-quality translations for many languages, they are still not on par when it comes to translating domain-specific terms. Today’s large-scale language models (LLMs) such as Llama-3 (Meta, 2024) can be fine-tuned using limited data (even with a few instances) for domain adaptation, making them a valuable resource for addressing domain-specific challenges in natural language processing (NLP). However, such domain-adapted models are found to have difficulty accurately translating domain-specific terminology. To the best of our knowledge, there has been very little attempt to address this crucial problem in MT. This PhD proposes to investigate different methods to improve terminology translation in NMT models (especially LLMs), e.g. in-context learning with terminology example, glossary-constrained decoding, agentic retrieval-augmented generation with termbases, low resource translation.
Initially (year one), the PhD candidate will focus on learning fundamental NLP methods and text analytics techniques. In parallel, but particularly in year two, the candidate will identify the objectives and research activities to be developed and advance the state of the art on the problems by developing technological innovations. The PhD candidate will be encouraged to develop collaborations with the researchers in the Twin Transition Centre, ADAPT Centre and Walton Institute, SETU’s EU Connexus Parter Institute La Rochelle University, IRISA, University of Rennes, and may also spend part of the research activity abroad or in industry.
Qualifications:
Essential
- Honours Degree (minimum 2:1) in the specific area or related area including computer science, mathematics, engineering or similar technical discipline. Other qualifications in disciplines related to the PhD topic will also be considered.
Desirable
- Master’s Degree (preferable 2:1) in the specific area or related area including computer science, mathematics, engineering or similar technical discipline. Other qualifications in disciplines related to the PhD topic will also be considered.
Knowledge & Experience
Essential
- Good mastery of Python programming
- Strong understanding of research philosophy, theory and methodology
- Strong interest in, and understanding of, the topics of NLP/MT
- Knowledge of qualitative and quantitative research methods
- Excellent writing, presentation and communication skills
- Applicants must demonstrate a genuine interest in/motivation towards the area of deep learning and computational linguistics.
Desirable
- Experience in NLP / Computational Social Science / Machine Learning / Data Science would be a plus
- Experience of organising and conducting a variety of quantitative and qualitative research techniques and methods
Skills &Competencies
Essential
- Applicants whose first language is not English must demonstrate on application that they meet SETU’s English language requirements and provide all necessary documentation. See Page 7 of the Code of Practice
- In order to be shortlisted for interview, you must meet the SETU English speaking requirements so please provide evidence in your application.
- Ability to work as part of a dynamic, multi-disciplinary team
- Strong analytical and problem-solving skills
- Motivation and capability of working independently
- Strong team player skills and commitment to the highest professional standards
Ability to meet a variety of internal and external deadlines
Desirable
- Python Scientific and data processing libraries such as NumPy, SciPy
- ML/DL libraries such as Scikit-learn, Keras and Tensorflow
- Skills in data analysis, visualisation and interpretation
Further information
For any informal queries, please contact Dr Rejwanul Haque by email Rejwanul.Haque@setu.ie
Application procedure
Complete the online Application Form from the SETU website quoting the advert reference code SETU_2025_14_CW.
Please ensure that you upload all supporting documents as part of your submission.
Please note that applications must be submitted by this route.
For queries relating to the application and admission process please contact the Postgraduate Admissions Office via email researchadmissions@setu.ie or telephone +353 (0)51 302883.
University Website: https://www.setu.ie
The University will short-list and interview those applicants who provide the most suitable information in terms of experience, qualifications and other requirements relevant to the scholarship.
SOUTH EAST TECHNOLOGICAL UNIVERSITY (SETU) IS AN EQUAL OPPORTUNITIES EMPLOYER
Where to apply
- Website
- https://www.setu.ie
Requirements
- Research Field
- Computer science
- Education Level
- Bachelor Degree or equivalent
Additional Information
Work Location(s)
- Number of offers available
- 1
- Company/Institute
- South East Technological University
- Country
- Ireland
- Geofield
Contact
- City
Carlow- Website
http://www.setu.ie- Street
Kilkenny Road- Postal Code
R93 V960
STATUS: EXPIRED
- X (formerly Twitter)
More share options- Viadeo
- Gmail
- Blogger
- Qzone
- YahooMail