Our research projects can be grouped into four themes:
- Computer-assisted language learning (which includes projects related to computer-assisted language learning, readability, etc.: ReSyF, Amesure, ...)
- Information processing (which includes projects connected with information extraction, information retrieval, textclassification, etc.: iMediate, Capadis, ...)
- (Socio-)linguistics of new media (Vos Pouces pour la Science, SMS4Science, ...)
- Medical language analysis (iMediate, Capadis, ...)
Language learning is a particularly crucial issue in our multilingual and multicultural society. In order to promote this learning process (at a time when learners are under ever-increasing pressure), Computer Assisted Language Learning (CALL) opens up a number of perspectives by taking advantage of related disciplines: NLP, language pedagogy, readability, psycholinguistics, etc. Research in this field aims at developing new algorithms and new linguistic resources useful for the design of language learning or evaluation tools.
IRE - Information Retrieval and Extraction
CENTAL is specialized in the development of semantic search engines, specialized for particular domains. It has notably designed the UCL search engine and indexing tools for the UCLouvain’s Archives Department.
SLIME - (Socio-) Linguistics of New Media and Business
In the age of new media, the SLIME group studies the psycholinguistic and sociolinguistic skills we use to communicate and the linguistic or semiotic relays that we mobilize to express ourselves. How does language, and more broadly communication practices, vary with new practices and new technologies? How do politicians and companies play with their image through these new multiplied media? Research in this field uses both qualitative and quantitative approaches, using automatic language processing as a tool for speech analysis.
MEDITAL - Medical Language
In the age of multimedia, text remains one of the essential tools of information in most companies (reports, minutes, letters, courses, encyclopedia, etc.). The medical field is no exception to this reality: in hospitals, and in particular since the advent of computerized patient records, large amounts of information are stored in the form of unstructured or poorly structured texts (consultation letters, discharge letters, operating protocols, imaging reports, etc.). By specializing NLP tools, we can therefore create "intelligent" tools capable of processing medical texts on a large scale, which is a key issue for improving patient safety, the quality of care and the administrative management of hospitals.