Lead AI research at DiliTrust. Building machine learning pipelines for contract analysis from R&D to production deployment. I'm currently leading DiliTrust's R&D team to improve our product and introduce new AI based features while exploring and advancing state of the art approaches in the legal domain.
French session - Beginner
Le Traitement Automatique du Langage (TAL) alimente de nombreuses technologies modernes telles que les chatbots ou la détection de spam. À la base du TAL se trouve le besoin de comprendre du texte—les octets bruts ne permettent pas d'extraire un réel sens. Cela justifie alors l'utilisation de représentations sophistiquées que nous introduisons ici: comptage (ex. TFIDF), vecteurs statiques (ex. word2vec) et réseaux de neurones (ex. Transformers).
English session - Advanced
Applying AI to real world problems in a supervised fashion requires large set of data covering all aspects of the problem we are solving. In reality, it’s impossible to build such dataset thus giving our model limited understanding of the problem leading to absurd predictions. The solution is Contrastive Learning which learns similarities and differences by contrasting samples against each other therefore limiting the need for human supervision.