no code implementations • 29 Sep 2021 • Mathias Etcheverry, Dina Wonsever
Antonymic and synonymic pairs may both occur nearby in word embeddings spaces because they have similar distributional information.
no code implementations • LREC 2020 • Gun Woo Lee, Mathias Etcheverry, Fern, Daniel ez Sanchez, Dina Wonsever
This paper addresses the task of supervised hypernymy detection in Spanish through an order embedding and using pretrained word vectors as input.
no code implementations • ACL 2019 • Mathias Etcheverry, Dina Wonsever
Discriminating antonyms and synonyms is an important NLP task that has the difficulty that both, antonyms and synonyms, contains similar distributional information.
no code implementations • 17 Oct 2017 • Aiala Rosá, Luis Chiruzzo, Mathias Etcheverry, Santiago Castro
This article presents classifiers based on SVM and Convolutional Neural Networks (CNN) for the TASS 2017 challenge on tweets sentiment analysis.
no code implementations • LREC 2016 • Mathias Etcheverry, Dina Wonsever
Contents analisys from text data requires semantic representations that are difficult to obtain automatically, as they may require large handcrafted knowledge bases or manually annotated examples.