English

LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish

Computation and Language 2019-06-19 v1

Abstract

This paper details LTG-Oslo team's participation in the sentiment track of the NEGES 2019 evaluation campaign. We participated in the task with a hierarchical multi-task network, which used shared lower-layers in a deep BiLSTM to predict negation, while the higher layers were dedicated to predicting document-level sentiment. The multi-task component shows promise as a way to incorporate information on negation into deep neural sentiment classifiers, despite the fact that the absolute results on the test set were relatively low for a binary classification task.

Keywords

Cite

@article{arxiv.1906.07599,
  title  = {LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish},
  author = {Jeremy Barnes},
  journal= {arXiv preprint arXiv:1906.07599},
  year   = {2019}
}

Comments

Accepted in NEGES (Negation in Spanish) workshop at SEPLN 2019