VinNLP

About Us

Who We Are

VinNLP is the Natural Language Processing (NLP) research group at VinUniversity, dedicated to advancing AI-driven language technologies with a strong focus on low-resource languages, machine learning, and applied NLP research.

We collaborate with academic institutions, industry partners, and government bodies to develop cutting-edge LLMs, text summarisation techniques, machine translation models, and more.

Our Mission

Our mission is to push the boundaries of NLP research by developing language technologies for underrepresented languages, improving multilingual AI, and contributing to the global AI research community.

Our Focus Areas

Low-resource language modelling
Text summarisation & information extraction
Machine translation & multilingual NLP
AI applications in healthcare, finance, and social sciences
Ethical AI and bias mitigation in NLP

We are part of VinUniversity’s College of Engineering and Computer Science (CECS) and collaborate with leading international research groups to create impactful AI-driven solutions.

VinNLP Leaders

Dr. Mo El-Haj

Director, VinNLP
Associate Professor (Reader) in NLP

Research focus: LLMs for low-resource languages, text summarisation & information extraction.

Prof. Wray Buntine

Professor in NLP
Director, Computer Science Program

Research focus: Probabilistic graphical models, deep learning, and NLP.

Dr. Le Duy Dung

Assistant Professor, Computer Science
Director of Data Science Program

Research focus: Data science, AI applications, and data-driven NLP research.

Researchers and PhD Students

Our group supports PhD students working on NLP-related research.

[Kieu Hai Dang] – Research focus: [Research Topic]
[Vo Diep Nhu] – Research focus: [Research Topic]
[Ta Quang Hieu] – Research focus: [Research Topic]
[Nguyen Tien Dong] – Research focus: [Research Topic]

Apply to join our research group as a PhD student Explore professional opportunities with our NLP team Explore professional opportunities at VinUniversity

Research & Projects

Research Projects

Projects by Dr Mo El-Haj
New: English-Vietnamese Free-Text Survey Analysis (FreeTxt-Vi) [Văn Bản Tự Do]
New: Vietnamese Semantic Tagging System (ViSaS)
Welsh Language Model (a pilot)
DigiGrid for Welsh Language Resources
Using NLP to Monitor Water Pipes Burst
Catalyst Fund for Advancing Celtic NLP Research
FreeTxt: Supporting Bilingual Free-Text Survey and Questionnaire Data Analysis
Talent Track Application for NLP and Econometric Techniques
Canadian Annual Reports Extractor (CARE)
Using Word Embeddings to Create a Thesaurus of Contemporary Welsh
Welsh Summary Creator (WSC)
CLARA-Fin: Readability and Simplification in Financial Narrative
An Assessment of Corporate Disclosures from Accounting Standards
Arabic USAS Semantic Tagger (AraSAS)
FinT-esp: Financial Texts in Spanish
Projects by Prof. Wray Buntine
Robust Vietnamese-English Clinical and Educational
Medical Translation
Towards Reliable Output Generation from LLMs
Verifiable Logical Reasoning with Language Models
Low-Resource Medical Named Entity Recognition
Improving Data Labelling Efficacy with Deep Neural
Network via Active Learning
Data-Driven Closed-Loop Medication Management
Deep Anomaly Detection on Graph-structured Data
Statistical Machine Learning Methods for Modelling
Imaging, and Monitoring the Brain
Projects by Dr Le Duy Dung
Robust Vietnamese-English Clinical and Educational
Medical Translation (PI: Prof. Wray Buntine)
Language Processing Adaptations for Multiple Recommendation Tasks (PI)
Multimodal Federated Learning for Multi-objectives Recommendation (PI)
SMART-CEM: Applying Artificial Intelligence (AI) and eye-tracking in designing and managing delightful customer experiences in the hospitality sector (Co-PI)