
Academic lab · Msida, Malta
MLRSUniversity of Malta
The University of Malta project that builds open corpora, tools and language models for Maltese, a language with few digital resources.
Msida, Malta
- Type
- Academic lab
- Based in
- Msida, Malta
- Key papers
- 1
- Featured projects
- 4
About
The Maltese Language Resource Server is a University of Malta project that produces tools and resources for Maltese, English and Maltese Sign Language. It is coordinated by the Institute of Linguistics and Language Technology together with the Department of Artificial Intelligence.
The server hosts Korpus Malti, an annotated corpus of roughly 250 million tokens in its version 3.0, as well as a learner corpus, an open lexicon and a sign language dictionary. A 2016 electronic Maltese dictionary built on the group's lexicon was launched with the Malta Communications Authority.
More recently the group has released Maltese language models and datasets on Hugging Face under the MLRS organisation, for researchers and developers working on Maltese.
Mission and ambitionsThe project aims to supply the open language data and software that Maltese needs to be supported by modern language technology.
Known for
- 01
Korpus Malti Maltese text corpus
- 02
Open Maltese language models on Hugging Face
- 03
Maltese part-of-speech tagging resources
- 04
Online Maltese dictionary
Milestones
- 2006
MLRS project described in print
An early paper describes the Maltese Language Resource Server as a two-year research project at the University of Malta.
- 2016
Korpus Malti v3.0 tagged
Version 3.0 of the corpus was annotated with an SVMTool tagger reporting about 97 percent accuracy.
- 2016
Official online Maltese dictionary launched
A dictionary built on the group's lexicon was launched with the Malta Communications Authority in March.
- 2022
Maltese BERT models released
The group published new corpora and BERT-style models for Maltese on Hugging Face.
Open source
- MLRS/BERTumodel
Model with 7 likes on the Hub.
- MLRS/mBERTumodel
Model with 4 likes on the Hub.
- MLRS/korpus_maltidataset
Dataset with 9 likes on the Hub.
- MLRS/MELABenchspace
Space with 0 likes on the Hub.
Research papers
Notable releases
Openness
Models and corpora are published on the MLRS Hugging Face organisation and the MLRS site.
People
- Albert GattCollaborator, language technology researcher
- Claudia BorgResearcher, Department of AI
- Mike RosnerOriginator of the project
- Kurt MicallefResearcher on Maltese language models
Listed from the lab's own pages and public profiles.
Contact and community
Contact via the site.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



