I am currently a Senior Applied Scientist at G42 Healthcare in Abu Dhabi, UAE. I am specialized in NLP projects for the healthcare sector: training LLMs, NER, NEL, information extraction. I am working with large models and very big data in order to improve patient care in the UAE.
2023-Current - Senior Applied Scientist, NLP @ G42
2017-2023 – Data Scientist, Researcher @ EDF R&D
I worked as a Research Engineer / Data Scientist for the Research & Development department of EDF, the French main electricity provider. I worked on my Ph.D. with EDF and ERIC Laboratory of University Lyon 2 until March 2021 when I defended my work on “Detecting novelty as soon as possible on textual data streams”. I was working on several NLP projects in order to increase client satisfaction but also on anomaly detection algorithms for time series of electricity production data.
January – July 2017 – Assistant Researcher. @ Eric Lab
Topic: “Detection of weak signal using probabilistic methods”. Weak signal can easily be confused with noise. I used natural language processing and topic-modeling techniques in order to detect novel documents in text streams related to customer feedback. I proposed and developed a software in Python (Numpy, Gensim) that can compare topics built with different corpora and extract novel document.
2018-2021 – PhD Student working on “Novelty Detection in textual data streams” under the supervision of Julien Velcin and Jairo Cugliari. @ Eric Lab and EDF
2012-2017 – Master’s degree in Telecommunication and Network Engineering with specialization in distributed architectures, big data and machine learning. @ IMT Lille-Douai
Monitoring geometrical properties of word embeddings for detecting the emergence of new topics In Empirical Methods in Natural Language Processing, EMNLP 2021. Clément Christophe, Julien Velcin, Jairo Cugliari, Manel Boumghar, Philippe Suignard
Change detection in textual classification with unexpected dynamics. In Expert Systems with Applications, ESWA 2021. Clément Christophe, Julien Velcin, Jairo Cugliari, Philippe Suignard, Manel Boumghar
How to detect novelty in textual data streams? A comparative study of existing methods. In AALTD Workshop @ECML-PKDD 2019. Clément Christophe, Julien Velcin, Jairo Cugliari, Philippe Suignard, Manel Boumghar
Utilisation de techniques de modélisation thématiques pour la détection de nouveauté dans des flux de données textuelles. In EGC 2018, vol. RNTI-E-34, pp.239-250.Clément Christophe, Julien Velcin, Manel Boumghar
Détection de nouveauté au plus tôt dans des flux de données textuelles. Clément Christophe, defended on March 15th 2021