Recent & Upcoming Talks

2020

Des Méthodes de TAL modernes pour l'Enrichissement de Documents

Nous présentons une pipeline pour le traitement et l’enrichissement de documents basée sur les dernières méthodes d’apprentissage neuronal.

Sep 22, 2020 10:30 AM — 12:00 PM Salle Weil, ENS.

Pedro Javier Ortiz Suárez

Diapositives Follow

A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages

We explore the impact of the training corpus on contextualized word embeddings in five mid-resource languages.

Jul 6, 2020 11:00 AM — 2:00 PM Online

Pedro Javier Ortiz Suárez, Laurent Romary, Benoît Sagot

Diapositives Vidéo Follow

A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages

2019

Asynchronous Pipeline for Processing Huge Corpora on Medium to Low Resource Infrastructures

We propose a new pipeline to filter, clean and classify Common Crawl by language, we publish the final corpus under the name OSCAR.

Jul 22, 2019 9:30 AM — 10:00 AM Cardiff, UK

Pedro Javier Ortiz Suárez, Benoît Sagot, Laurent Romary

PDF Code Diapositives Follow

Preparing the Dictionnaire Universel for Automatic Enrichment

A talk about automatic enrichment of dictionaries.

Jun 13, 2019 11:00 AM — 11:30 AM Leeuwarden, Pays-Bas

Pedro Javier Ortiz Suárez, Laurent Romary, Benoît Sagot

Diapositives Follow

Reducing computation time by months by rewriting Bash scripts in Go

Mar 24, 2019 7:00 PM — 10:00 PM La Base

Pedro Javier Ortiz Suárez

Code Diapositives Follow