Papers by Marc Pàmies

2 papers
XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection (2020.coling-main)

Copied to clipboard

Challenge: XED is a multilingual fine-grained emotion dataset for English and other low-resource languages.
Approach: They propose a multilingual fine-grained emotion dataset using Plutchik's Wheel of Emotions and a projection scheme to annotate Finnish and English sentences.
Outcome: The proposed dataset is based on human-annotated Finnish and English sentences and projected annotations for 30 additional languages.
A weakly supervised textual entailment approach to zero-shot text classification (2023.eacl-main)

Copied to clipboard

Challenge: Existing methods to train on weakly supervised datasets are expensive due to the computational cost of pre-training.
Approach: They propose a method that trains on a weakly supervised dataset that is used as a proxy for a textual entailment problem and a target zero-shot text classification task.
Outcome: The proposed model achieves state-of-the-art performance in the scientific domain and competitive results in other areas.

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