Skip to main content
EU Science Hub

Guillaume Jacquet

Guillaume Jacquet is a research scientist in Computational Linguistics, with specialisation in multilingual and cross-lingual text analysis.

Portrait of Guillaume Jacquet

Biography

Guillaume Jacquet is a research scientist in Computational Linguistics, with specialisation in multilingual and cross-lingual text analysis. He joined the Joint Research Centre - European Commission in 2013, and currently works in the Text and Data Mining Unit (Ispra, Italy). He is Scientific Project Officer in the Competence Centre on Text Mining and Analysis, and he contributes to the development of the Europe Media Monitor (EMM) family of news analysis applications as well as the Tools for Innovation Monitoring (TIM) project.

EMM gathers an average of about 300,000 online news articles per day in about seventy languages from thousands of online news sources. EMM pre-processes the multilingual news automatically, using Language Technology methods, to support information-seeking users in their daily work. EMM users include the European institutions, the EU's Member States, international organisations and the general public.

TIM Technology tools aim at providing specific and relevant knowledge on innovation and technological development. The objective is to offer the possibility to policy-makers to answer concrete policy needs related to innovation networks, impact evaluation of EU programmes, emerging trends and technologies, funding orientations, regional strategies, and other needs related to research and innovation policy.

Guillaume contributes to the development and improvement of Text Mining tools such as:

  • Multilingual Named Entity Guessing: new/unknown Named Entity detection.
  • Acronym resolution: linking short and long forms related to the same entity in a multilingual environment.
  • Developing and integrating Linked Open Data in existing NLP tools.
  • Developing Hybrid methods (combining rule based, statistical and machine learning approaches) for information extraction from text.

Main scientific interests: Computational Linguistics; Text Mining; Natural Language Processing; Machine Learning; Information Extraction; Named Entity Recognition (persons, organisations, geographic locations, events and more); Textual Entailment, Word Sense Disambiguation.

Career History: Guillaume defended his Ph.D. in 2005 in the field of Cognitive Sciences/Computational Linguistics from the academic consortium Ecole des Hautes Etudes en Sciences Sociales / Ecole Normale Supérieure / University of Paris 6 / Ecole Polytechnique in Paris. During his Ph.D, he was a Research Engineer in the Lattice CNRS/ENS lab. From 2006 to 2013, he worked as a Research Scientist at the Xerox Research Centre Europe (acquired in 2017 by Naver - Naver Labs Europe) in Grenoble (France). From 2002 to 2012, he taught at both undergraduate and graduate level, as a Sessional lecturer, at the University of Paris-Dauphine and University of Grenoble Stendhal.

Publications:

JRC's Publications Repository

Guillaume's Google Scholar profile