BI-FR/23-24-PROTEUS-006

Recognizing, extracting and aligning domain-specific terms is useful in various fields, such as
translation, dictionary creation, ontology generation and others, remains a difficult task. Automated
terminology extraction refers to the task of extracting meaningful terms from domain-specific texts,
while terminology alignment represents the task of aligning terms across languages. Automated
methods to terminology management have been the subject of research for a long time, but state-of-the-
art performance often lags behind other natural language processing tasks.

In our project, we will focus on novel methods using contextual embeddings.