About me.
I am a computer scientist and data scientist. Currently I work as an applied researcher in text mining and natural language processing (NLP) in projects on Document Processing at Fujitsu's Center of Excellence (CoE) (Data Intelligence).
In general, I am interested in the efficient exploitation of information in unstructured data, in particular, in the biomedical and social media domains, mainly in low resource languages and/or code-switching. I also enjoy collecting and processing text data, creating corpora/data sets and building machine learning (ML) models.
Check my CV Resume and Publications.
Research, projects and so on...
My dissertation is on ML approaches for topic discovery and sentiment analysis in multilingual/code-switched opinions and low-resource languages. Where I studied text written in English, Spanish, Guarani and Guarani-Spanish code-switching (called Jopará and sometimes Jehe'a).
Here is my Google Scholar profile (publication's citations) and my LinkedIn profile (professional network).
Also, check out my ResearchGate profile (academic network) and my open-source code and open-source ML models repositories, to see examples of my work.
See our Guarani (gn) LLMs collection (including our set of pre-trained BERT models on only ~800K tokens from the Wikipedia) and choose the best one for you ;).
I was born in Areguá and grew up in Luque near to Asunción, the capital city of Paraguay (in the heart of South America).
Contact.
El Puerto de Santa María, Spain
marvin(hyphen)aguero(at){hotmail|outlook}(dot)com
marvin(dot)aguero(dot)torales(at)gmail(dot)com