Abstract
In this presentation, I will first present an overview of more traditional ATE techniques: linguistic, statistical and hybrid. I will then look into the recent contributions from the fields of machine learning and artificial intelligence. More precisely, we will explore the potential use of word embeddings. Using simple algebraic operations, word embeddings allow for the comparison of semantic features of words. We will explore the potential contributions of word embeddings to structuring of the results of a hybrid ATE tool, TermoStat (http://termostat.ling.umontreal.ca).
Bio
Patrick Drouin is full professor at the Department of Linguistics and Translation of the Université de Montréal, where he teaches terminology and localization. He is also director of the Observatoire de linguistique Sens-Texte (OLST), an interdisciplinary research group working in the fields of lexicology and lexicography, terminology and terminography, natural language processing, information science and lexicon teaching. Patrick Drouin's research is funded by the Social Sciences and Humanities Research Council of Canada (SSHRC) and the Fonds de recherche du Québec en Société et Culture (FRQSC). His main interests are corpus linguistics, natural language processing applied to terminology and the scientific lexicon.