activity
20202022
most citedModel Interpretability through the Lens of Computational Complexity

38 citations · 50 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CL20221 cited

Cross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios

Cinthia Sánchez, Hernan Sarmiento, Andres Abeliuk +2

Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster managem…

cs.LO20221 cited

Asynchronous Functional Sessions: Cyclic and Concurrent (Extended Version)

Bas van den Heuvel, Jorge A. Pérez

We present Concurrent GV (CGV), a functional calculus with message-passing concurrency governed by session types. With respect to prior calculi, CGV has increased support for concu…

cs.LO20221 cited

Asynchronous Functional Sessions: Cyclic and Concurrent

Bas van den Heuvel, Jorge A. Pérez

We present Concurrent GV (CGV), a functional calculus with message-passing concurrency governed by session types. With respect to prior calculi, CGV has increased support for concu…

cs.CL2021

Cross-lingual hate speech detection based on multilingual domain-specific word embeddings

Aymé Arango, Jorge Pérez, Barbara Poblete

Automatic hate speech detection in online social networks is an important open problem in Natural Language Processing (NLP). Hate speech is a multidimensional issue, strongly depen…

cs.AI202038 cited

Model Interpretability through the Lens of Computational Complexity

Pablo Barceló, Mikaël Monet, Jorge Pérez +1

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a…

cs.LO2020

Session Coalgebras: A Coalgebraic View on Session Types and Communication Protocols

Alex C. Keizer, Henning Basold, Jorge A. Pérez

Compositional methods are central to the development and verification of software systems. They allow to break down large systems into smaller components, while enabling reasoning…