Hi there, my name is Jonathan and I am a PhD Candidate at Vrije Universiteit Amsterdam. The Computational Linguistics and Text Mining Lab is where my research is mainly carried out, advised by Prof. dr. Antske Fokkens and Prof. dr. Lisa Beinborn. My project falls under a larger consortium named InDeep: Interpreting Deep Learning Models for Text and Sound. I investigate how language models can be interpreted, with a focus on Argument Mining.

My background is in language studies (Spanish), intercultural communication, and linguistics (both theoretical and computational). Prior to the start of my PhD, I have been working as a Data Scientist at Converz Analytics, developing conversational AI technology.

In my free time you can find me hunting Strava KOMs on my Bianchi (nonesome so far) and sometimes in the virtual chess arena. Feel free to get in touch!

Updates

LREC-Coling 2024 in Turin: happy to be back in my home country with our paper on the linguistic preferences of post-hoc explanation methods. Perhaps these methods are not as random as they seem ;) :: Tweet with poster - May 23, 2024

EMNLP 2023 in Singapore: presenting our latest paper on (dis)agreement between feature attribution methods and a way of selecting the top-k important tokens. Volunteering at the conference was a pleasant way of getting to know (more) people :) :: Tweet with poster - December 9, 2023

M2L, the Mediterranean Machine Learning summer school organised by Google Deepminders was last week. I happened to be there, and it was great to connect with so many people. The big questions is: what is research for you? :: Link - September 5, 2023

Connecting research: together with colleagues from VU and Leiden University, we made a visit at GroNLP where we presented our work on computational argumentation and deliberation from different research angles! :: Tweet - February 24, 2023

Happy that I pitched my ideas on post-hoc interpretability at the 2nd Interdisciplinary Workshop on the Digital Society, organised by the Network Institute in Amsterdam. :: Event description - February 10, 2023

Moonlit just released the interview they had with me! Check it out if you want to get some idea of what my research on interpretability and (legal) argument mining is about! :: Interpreting machines that interpret language - December 6, 2022

Our paper got accepted! I will be presenting it at the 9th Workshop on Argument Mining on October 17th in Gyeongju, South Korea. :: Proceedings - September 15, 2022