ERTIM

NLP, generally considered to be a field of application of Artificial Intelligence (AI), draws on computer science, mathematics and linguistics. The main objective is to design or exploit means (models and algorithms) for analyzing or generating data in languages, according to a written or oral modality. Specific tasks are of various kinds: acquisition and digitization of textual data, linguistic or semantic modeling, information extraction, data mining, machine translation, dialogue systems, etc.

ERTIM is particularly interested in methodological issues (data collection, digitization, annotation, qualitative or quantitative evaluation) in highly multilingual contexts, with a strong interest in the poorly endowed languages of the Inalco domain. The team's activities are divided into four areas: digital humanities, language diversity, NLP methodology, linguistic information acquisition.