LIA at SemEval-2017 Task 4: An Ensemble of Neural Networks for Sentiment Classification

Mickael Rouvier


Abstract
This paper describes the system developed at LIA for the SemEval-2017 evaluation campaign. The goal of Task 4.A was to identify sentiment polarity in tweets. The system is an ensemble of Deep Neural Network (DNN) models: Convolutional Neural Network (CNN) and Recurrent Neural Network Long Short-Term Memory (RNN-LSTM). We initialize the input representation of DNN with different sets of embeddings trained on large datasets. The ensemble of DNNs are combined using a score-level fusion approach. The system ranked 2nd at SemEval-2017 and obtained an average recall of 67.6%.
Anthology ID:
S17-2128
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
760–765
Language:
URL:
https://aclanthology.org/S17-2128
DOI:
10.18653/v1/S17-2128
Bibkey:
Cite (ACL):
Mickael Rouvier. 2017. LIA at SemEval-2017 Task 4: An Ensemble of Neural Networks for Sentiment Classification. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 760–765, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
LIA at SemEval-2017 Task 4: An Ensemble of Neural Networks for Sentiment Classification (Rouvier, SemEval 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/S17-2128.pdf