Description:
Code-mixing, i.e., the mixing of two or more languages in a single utterance or conversation, is an extremely common phenomenon in multilingual societies. It is amply present in user-generated text, especially in social media. Therefore, CSS research that handles such text requires to process code-mixing; there are also interesting CSS and socio-linguistic questions around the phenomenon of code-mixing itself. In this tutorial, we will equip you with some basic tools and techniques for processing code-mixed text, starting with hands-on experiments with word-level language identification, all the way up to methods for building code-mixed text classifiers using massively multilingual language models.
Tutorial hosts: Monojit Choudhury & Sanad Rizvi
Slides: https://nlp-css-201-tutorials.github....
Code: https://colab.research.google.com/dri...
This is part of a larger tutorial series, NLP+CSS 201: Beyond the basics, which is organized by Ian Stewart and Katherine Keith. Website: https://nlp-css-201-tutorials.github....
Sur cette page du site, vous pouvez voir la vidéo en ligne Tutorial 11: Processing Code-mixed Text durée heure minute seconde en bonne qualité , qui a été Téléchargé par l'utilisateur NLP and CSS 201: Beyond the Basics 01 mai 2022, Partagez le lien avec vos amis et connaissances, sur youtube cette vidéo a déjà été regardée 1,700 fois et il a aimé 27 téléspectateurs. Bon visionnage!