💼 Experiences

---

 

PhD Student

Berger-Levrault

Sept. 2021 - Today | Toulouse, Occitanie, France

As a doctoral student in computer science at IRIT, I’m working on the extraction of regulatory information for Berger-Levrault. The aim of my work is to enable a computer system to extract and understand legal texts.

 

Teacher

Toulouse University

Sept. 2021 - Today | Toulouse, Occitanie, France

As part of my thesis, I was asked to teach a number of subjects to university students, including Java data structures, NoSQL databases and introduction to computer science (Pix).

 

Sopra Steria

3 years et 1 month

 

Software Development Engineer

Sept. 2020 - Sept. 2021 | Toulouse, Occitanie, France

Last assignment for my engineering degree. My job was to develop new features on Carl Source Software. This application is used to manage the maintenance assets.

 

Software Development Engineer

jan. 2021 - jun. 2021 | Toulouse, Occitanie, France

The goal of this mission was to create a connection between the two largest software editing companies. And create a proof of concept about using S/4HANA and Maximo together.

 

Développeur Android

jul. 2019 - Sept. 2020 | Toulouse, Occitanie, France

Apprenticeship at Sopra Steria in E.A.M. Factory mobile team. I worked with ReactiveX programming for La Poste client. The application has been interfaced with Maximo for a mobile management of the assets.

 

Développeur Java

Sept. 2018 - janv. 2020 | Toulouse, Occitanie, France

I worked on Maximo Asset Management. My mission was to implement new features according to client’s wishes. I was also in charge of the automated functional tests and work flow tools.

 

 

Chief Technology Officer

Vehoshop

jan. 2020 - Sept. 2021 | Toulouse, Occitanie, France

As a CTO, my job is to design and implement the back-end infrastructure of the application. I must deal with low-latency and clustering technologies.

 

 

Développeur web

METEO FRANCE

apr. 2018 - jul. 2018 | Toulouse, Occitanie, France

Internship at Météo-France in order to create a Web interface which consumes large meteorological data for professionals. Immersion in the weather forecasting process.

 

 

🕹️ Experiences personnelles

---

Crackito : open source coding game plateform

To make university practical work more interesting, I decided to develop a coding game platform. This allows you to manage the progress of your exercises in a fun way.

 

 

Personal HomeLab (datacenter)

With the aim of protecting my personal data and understanding the field of data center and cloud infrastructure, I decided to build my own HomeLab.

 

 

📜 Publications

---

 

Semantic Model for the Legal Maintenance: the Case of Semantic Annotation of France Legislative and Regulatory Texts

14 Dec. 2022 | LN2FR

In different domains, compliance with legal documents about industrial maintenance is crucial. Legal industrial maintenance is the legal commitment of a company to control, maintain and repair its equipments. With the evolution of legal texts, companies are increasingly adopting automatic processing of legal texts in order to extract their key elements and to support the task of analysis and compliance. To perform such a task of knowledge extraction, a number of state-of-the-art proposal relies on a semantic model. Based on existing models from both legislative and industrial maintenance domains, we propose a new semantic model for the legal industrial maintenance: SEMLEG (SEmantic Model for the LEGal maintenance). This model results from an analysis of documents extracted from the Légifrance French governmental website.

 

 

BL.Research at SemEval-2022 Task 1: Deep networks for Reverse Dictionary using embeddings and LSTM autoencoders

1 Jul. 2022 | ACL

This paper describes our two deep learning systems that competed at SemEval-2022 Task 1 “CODWOE: Comparing Dictionaries and WOrd Embeddings”. We participated in the subtask for the reverse dictionary which consists in generating vectors from glosses. We use sequential models that integrate several neural networks, starting from Embeddings networks until the use of Dense networks, Bidirectional Long Short-Term Memory (BiLSTM) networks and LSTM networks. All glosses have been preprocessed in order to consider the best representation form of the meanings for all words that appears. We achieved very competitive results in reverse dictionary with a second position in English and French languages when using contextualized embeddings, and the same position for English, French and Spanish languages when using char embeddings.This

 

 

🎒 Education

---

 

PhD student in natural language processing and artificial intelligence

Sept. 2021 - Today | Toulouse, Occitanie, France

 

 

Engineering school in computer science (4th)

Sept. 2018 - Sept. 2021 | Rodez, France

 

 

International semester in neuronal network

Sept. 2020 - Feb. 2021 | UTS, Sofia, Bulgaria

 

 

University Institute of Technology in computer science (7th)

Sept. 2016 - Sept. 2018 | Toulouse, Occitanie, France