Search Results for author: Ruben Branco

Found 10 papers, 3 papers with code

Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning

1 code implementation EMNLP 2021 Ruben Branco, António Branco, João António Rodrigues, João Ricardo Silva

Commonsense is a quintessential human capacity that has been a core challenge to Artificial Intelligence since its inception.

Assessing Wordnets with WordNet Embeddings

1 code implementation GWC 2019 Ruben Branco, João Rodrigues, Chakaveh Saedi, António Branco

An effective conversion method was proposed in the literature to obtain a lexical semantic space from a lexical semantic graph, thus permitting to obtain WordNet embeddings from WordNets.

Semantic Similarity Semantic Textual Similarity +1

Transfer Learning of Lexical Semantic Families for Argumentative Discourse Units Identification

no code implementations6 Sep 2022 João Rodrigues, Ruben Branco, António Branco

Experimental results show that transfer learning techniques are beneficial to the task and that current methods may be insufficient to leverage commonsense knowledge from different lexical semantic families.

Argument Mining Transfer Learning

Comparative Probing of Lexical Semantics Theories for Cognitive Plausibility and Technological Usefulness

no code implementations COLING 2020 António Branco, João Rodrigues, Małgorzata Salawa, Ruben Branco, Chakaveh Saedi

Lexical semantics theories differ in advocating that the meaning of words is represented as an inference graph, a feature mapping or a vector space, thus raising the question: is it the case that one of these approaches is superior to the others in representing lexical semantics appropriately?

Reproduction and Revival of the Argument Reasoning Comprehension Task

no code implementations LREC 2020 Jo{\~a}o Ant{\'o}nio Rodrigues, Ruben Branco, Jo{\~a}o Silva, Ant{\'o}nio Branco

Given a recent publication that pointed out spurious statistical cues in the data set used in the shared task, and that produced a revised version of it, we also evaluated the reproduced systems with this new data set.

Predicting Brain Activation with WordNet Embeddings

1 code implementation WS 2018 Jo{\~a}o Ant{\'o}nio Rodrigues, Ruben Branco, Jo{\~a}o Silva, Chakaveh Saedi, Ant{\'o}nio Branco

The task of taking a semantic representation of a noun and predicting the brain activity triggered by it in terms of fMRI spatial patterns was pioneered by Mitchell et al. 2008.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.