Spanish NLP - Introductions

¡Hola y bienvenidos! :mexico: :colombia: :es: :argentina: :peru: :venezuela: :chile: :ecuador: :guatemala: :cuba: :bolivia: :dominican_republic: :honduras: :paraguay: :el_salvador: :nicaragua: :costa_rica: :panama: :uruguay: :equatorial_guinea: :puerto_rico:

This is the introduction thread for Spanish NLP practitioners. Please introduce yourself by telling us a little bit about:

  • Your name, Github, Hugging Face, and/or Twitter handle
  • Your interest in Spanish NLP
  • Some projects you are working on or interested in starting
  • Any other languages that you speak, any personal interests, or anything else :dancer:

As for me, I’m Lewis (@lewtun on GitHub / :hugs: Hub, @_lewtun on Twitter) and I’m a data scientist in Switzerland where I build ML-powered applications for startups and enterprises, mostly in the domains of NLP :open_book:, time series :chart_with_upwards_trend:, and topological data analysis :doughnut:.

I spent a big chunk of my childhood living in Chile, which is why I’m interested in Spanish NLP :smiley:

My most recent project with Transformers involved applying XLM-R to improve the routing accuracy of customer support tickets in the 3 major Swiss languages (German, French, and Italian). I’m personally interested in making Transformers efficient through techniques like distillation, quantization, and pruning, because deploying these large models in the real-world is no mean feat!

Looking forward to e-meeting you all!


Hola a tod@s! :relaxed:

Thanks @lewtun for kicking off this thread introducing yourself!

I’m Maria and my handle is @mariagrandury on GitHub, :hugs:Hub and LinkedIn.

I’m from Spain - from Ponferrada, in the northwest - and currently I’m living in Berlin. I’m a Research Engineer at a startup here called neurocat and focused on AI quality and trustworthiness (i.e. explainability, robustness, performance and ethics).

I’m very interested in the intersection of all these topics with NLP and also in the application of AI to biomedicine, in particular the use of NLP techniques and architectures like Transformers to work with text-based representations of molecules (e.g. SMILES).

I’m looking forward to reading your introductions and seeing this community grow! :rocket:

Hasta pronto! :hugs:



I’m Eduardo! Here is my huggingface profile, my Github and Linkedin.

I am from Madrid, Spain and currently living in San Francisco, California. I am a ML Engineer at Ferrum Health, a startup developing a ML platform for patient safety. My background is in Biomedical Engineering and Neurotechnology.

In my current role, I use transformers to process radiological reports, in combination with computer vision models to detect diagnosis errors.

I am passionate about the intersection of AI and healthcare and bringing state-of-the-art Machine Learning into hospitals to improve healthcare outcomes.

Looking forward to hearing more about you all! :hugs:


Hola a tod@s!

I’m Isaac (@IsaacRodgz | Github | LinkedIn ).

I’m from Mexico, living in Mexico City. I’m finishing my MSc. in CS and currently working in multimodal learning with transformer architectures (MMBT, MulT, ViLBERT, etc.). Also interested in Transfer Learning, where I am exploring Adapter modules, either for multilingual tasks or other problems.

Other interests in AI involve interpretability of Transformer models and making them more efficient. In the future I would like to dig deeper in Chatbots based on Transformer architectures.

Look forward to hearing and learning from you all :hugs:


¡Hola a tod@s!

Ryan here (@rydcunningham | LinkedIn). I’m originally from Texas and currently living between San Francisco and Park City, Utah. I’m an AI Product Manager at Spiketrap, an NLP startup with a suite of APIs for hate speech detection, sentiment analysis, and more. We’re in the process of expanding our native language support, hence the interest in the forums!

Part-time, I’m studying AI at Stanford with a focus on NMT with transformer architectures and model compression for edge deployments. I also write about the intersection of AI, economics, and product in my biweekly newsletter Machine Yearning.

I’m very interested in learning from other MLEs and ML researchers from outside the mainstream AI communities (e.g. US and China), especially in NLP. Spanish is one of the three largest global languages, and I’m looking forward to seeing what innovations can come out of the space when not dominated by hype-y headlines of a US vs. China arms race.

Looking forward to engaging with and learning from all of you!


Hello everyone!!! Hola a tod@!!!

My name is Nacho, (Huggingface: @Ignacio) | Linkedin | Twitter |

I’m living in Lorca (Murcia) Spain, I’m working at the Hospital University “Rafael Méndez”. I collaborate with the University of Murcia, with the A.I.K.E. Research Group and as Mentor and Alpha tester of

My interest is the NLP applied to clinical terminologies. (Snomed-CT).
I have some works based on word embedding (Word2Vec), to develop a clinical NER. (Snomed2Vec)

Now I want to make the leap to Transformers with BERT and apply it with clinical texts.

Looking forward to hearing more about you all! Keep Learning…!!!


Muy buenas!!

My name is Antonio Polo (Linkedin | Huggingface) and I am currently living in Bilbao. I am working at Nymiz, NLP startup focus on protecting company’s personal data.

On the other hand, I am specially interested in interpretability techniques ( actually my master thesis was focus on SHAP values and other methods like LIME ).

I have been working in several startups and learning from different fields of artificial intelligence since I started in university. So, I am willing to know what you are doing!

I hope to learn a lot from this community and provide any help I can. :slight_smile: :hugs:


Hello everyone!

I am Daniel (@dpalominop | Github | Linkedin).

I am from Peru, living in Lima. I am a NLP Engineer at, a swiss startup in Machine Learning and Topological Data Analysis.

Actually, I am focused on Language Modelling and Gans for language understanding and industry’s NLP applications. I am looking for a Phd program in Computer Science too :blush:.

Look forward to hearing and learning from you all :hugs:



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, including Spanish. 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.

Un abrazo :hugs:


Hola a todos!
I’m René Gómez from Colombia (LinkedIn). I’m currently in France, where I just finished my Master in Data Analytics. I have used Transformers :hugs: to benchmark some NER models in specific domains using noisy training sets.
I’m interested in NLU and looking forward to continuing working in the field, specifically conversational AI.
Ok, that’s all. Saludos parceros :grin:


Hola a todos, amigos de habla hispana!

My name is Francisco Ingham and I am a Data Scientist based in Buenos Aires Argentina. I have a business background, but have been working as a hands-on data scientist in Mercado Libre (e-commerce/fintech company in LatAm) for 2 years now, recently focusing on NLP problems.

In my job, I enjoy experimenting with BERT-family models on NLP classification downstream tasks to try to beat more traditional approaches. In my free time, I am specially interested in applying transformers to non-NLP sequences such as the recent Wav2Vec release which I’ve been meaning to investigate but have not had time for yet.

Looking forward to collaborating together :wave:!



I am Pablo Lopez (Linkedin), I am from Paraguay and have recently finished a Master Degree in CS at CentraleSupélec.

I worked with word embeddings :hugs: + Graph Conv Nets to build a semantic schema matching for datasets. I am interested in representation learning for graphs/knowledge graphs, and NLP in general!

Excited for the field and looking forward to keep learning from the community :slight_smile:


Hola de nuevo! We have created a Slack community where we share existing resources and organize ourselves to create new ones. Join us!

Únete a NLP en Español :hugs:

If you have any question don’t hesitate to reach out on LinkedIn!


Hi Maria!

Thank you for the slack link! However, it seems is not valid anymore, would you mind sharing a new one please? Looking forward to join :slight_smile:

Hi! The Slack link expires after 30 days, here is the new one!

Únete a NLP en Español :hugs:

Hi everyone! Thought you might be interested - there is a new HAHA competition to classify jokes in Spanish as funny or not, and what type of joke it is. I participated a couple of years ago, it was good fun. Great community as well