CLJun 18, 2019

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

arXiv:1906.07599v11 citations
Originality Synthesis-oriented
AI Analysis

This work addresses sentiment analysis in Spanish, focusing on negation, but is incremental as it builds on existing multi-task learning approaches.

The paper tackled the challenge of incorporating negation information into document-level sentiment analysis for Spanish by proposing a hierarchical multi-task network, but achieved relatively low results on a binary classification test set.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes