Catalan NLP - Introduction

Oh, benvinguts, passeu passeu :musical_note: :musical_note:

This is the introduction thread for Catalan NLP enthusiasts. Albeit a “small” language, it has a strong internet presence, such as Viquipèdia and even some HF models! So let’s keep the wheel turning.

To get started, please introduce yourself with any of the following:

  • Your name, Github, Hugging Face, and/or Twitter handle
  • Some projects you are working on or interested in starting
  • Any potential directions you have in mind for the Hugging Face Italian community
  • Anything else you’d like to share!

My name is Pere-Lluís (@PereLluis13 | Github | Twitter), I come from Reus, hometown of Gaudí, the guy who built all the cool stuff in Barcelona but nothing in my hometown, however we still have the best vermouth.

I am currently doing a PhD at Babelscape and la Sapienza, in Rome. My work leverages NLP with Knowledge Graph related tasks such as Relation and Entity extraction, with a particular focus on Multilinguality. I also got a couple of publications during my MSc that used Huggingface, you can check them in Scholar.

I think Transformers are a given in any NLP research nowadays, and that includes Huggingface, so I am constantly using the library in my research. I am particularly interested in autoregressive models as well as interpretability.

Una abraçada :hugs:


Hi everybody,

My name is Albert Villanova del Moral (@albertvillanova , GitHub, Twitter), and I am from Alcoi (València, Spain), currently living in Paris (France).

I am a Data Scientist, and I collaborate with Hugging Face. My background is in Theoretical Particle Physics (PhD) and Computer Science (BSc).

In a broad sense, my main interests in NLP revolve around the development of Open Source language technologies (datasets and models) created collaboratively by and for the community, with a special emphasis on diversity, bias and underrepresented languages.

I hope that we manage to create and develop an interesting active community around the Catalan language, where we will be able to coordinate and collaborate so that our language does not miss this important train of the technology age.

Abraçades! :hugs: