Papers by João Ricardo Silva

3 papers
Universal Grammatical Dependencies for Portuguese with CINTIL Data, LX Processing and CLARIN support (2022.lrec-1)

Copied to clipboard

Challenge: a new collection of quality language resources is presented for the computational processing of the Portuguese language . the framework for the mapping between linguistic form and meaning is centered on the notion of grammatical relation .
Approach: They propose a new set of quality language resources for the computational processing of the Portuguese language under the Universal Dependencies framework.
Outcome: The proposed framework provides for the mapping between linguistic form and meaning representations.
Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning (2021.emnlp-main)

Copied to clipboard

Challenge: a recent study has found that commonsense reasoning models are learning transferable generalizations . commonsensibility is a human capacity that has been a core challenge to Artificial Intelligence since its inception.
Approach: They conduct an analysis of benchmarks that involve commonsense reasoning . they find that most datasets experimented with are problematic . commonsensence is a quintessential human capacity .
Outcome: The proposed model is able to perform well on commonsense reasoning tasks . the model is not learning transferable generalizations or taking advantage of shortcuts .
Hands-off Image Editing: Language-guided Editing without any Task-specific Labeling, Masking or even Training (2025.coling-main)

Copied to clipboard

Challenge: State-of-the-art approaches to this task resort to supervised training and labelling, masking or training.
Approach: They propose an approach that does without any task-specific supervision and offers thus a better potential for improvement.
Outcome: The proposed approach achieves very competitive performance and scales up in a way that requires no task-specific supervision.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations