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.

Pedro Javier Ortiz Suárez

Sep 22, 2020

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.

Pedro Javier Ortiz Suárez, Laurent Romary, Benoît Sagot

Jul 6, 2020

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.

Pedro Javier Ortiz Suárez, Benoît Sagot, Laurent Romary

Jul 22, 2019

Preparing the Dictionnaire Universel for Automatic Enrichment

A talk about automatic enrichment of dictionaries.

Pedro Javier Ortiz Suárez, Laurent Romary, Benoît Sagot

Jun 13, 2019

Reducing computation time by months by rewriting Bash scripts in Go

Pedro Javier Ortiz Suárez

Mar 24, 2019