activity
20162022
most citedDiscrete and continuous representations and processing in deep learning: Looking forward

29 citations · 60 across the 8 of their papers we have counts for

collaborators

15 papers

cs.CL2022

Evaluation Benchmarks for Spanish Sentence Representations

Vladimir Araujo, Andrés Carvallo, Souvik Kundu +6

Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate…

cs.CL20221 cited

Finding Structural Knowledge in Multimodal-BERT

Victor Milewski, Miryam de Lhoneux, Marie-Francine Moens

In this work, we investigate the knowledge learned in the embeddings of multimodal-BERT models. More specifically, we probe their capabilities of storing the grammatical structure…

cs.CV20223 cited

Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering

Mingxiao Li, Marie-Francine Moens

Knowledge-based visual question answering (VQA) is a vision-language task that requires an agent to correctly answer image-related questions using knowledge that is not presented i…

cs.NE202229 cited

Discrete and continuous representations and processing in deep learning: Looking forward

Ruben Cartuyvels, Graham Spinks, Marie-Francine Moens

Discrete and continuous representations of content (e.g., of language or images) have interesting properties to be explored for the understanding of or reasoning with this content…

cs.CV20218 cited

Revisiting spatio-temporal layouts for compositional action recognition

Gorjan Radevski, Marie-Francine Moens, Tinne Tuytelaars

Recognizing human actions is fundamentally a spatio-temporal reasoning problem, and should be, at least to some extent, invariant to the appearance of the human and the objects inv…

cs.CL2021

Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations

Vladimir Araujo, Andrés Villa, Marcelo Mendoza +2

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been…