@techreport{oai:ipsj.ixsq.nii.ac.jp:00212729,
 author = {Vuong, Thi Hong and Atsuhiro, Takasu and Vuong, Thi Hong and Atsuhiro, Takasu},
 issue = {3},
 month = {Sep},
 note = {Ensemble methods use multiple learning algorithms to obtain better predictive performance. Currently, deep learning models with multilayer processing architecture are showed that the performance is better than the traditional classification models. Ensemble deep learning models combine the advantages of both ensemble learning and deep learning such that the final model has better performance. This paper presents a novel ensemble deep learning method, achieving robust and effective sequence classification facing sparse data. We use the BERT (Bidirectional Encoder Representation from Transformers) as the word embedding method. Then, we integrate the BiLSTM (Bidirectional Long Short-Term Memory) and CNN (Convolutional Neural Network) with an attention mechanism for sequence classification. We evaluate our ensemble models with two datasets with the different baseline methods. The first dataset is from IMDB and contains 50,000 movie reviews, labeled with two sentiment classes. The second dataset is the Toxic Comment Dataset with more than 150,000 comments for six classes. The experimental results show that our proposed method provides an accurate, reliable, and effective solution for sequence data classification., Ensemble methods use multiple learning algorithms to obtain better predictive performance. Currently, deep learning models with multilayer processing architecture are showed that the performance is better than the traditional classification models. Ensemble deep learning models combine the advantages of both ensemble learning and deep learning such that the final model has better performance. This paper presents a novel ensemble deep learning method, achieving robust and effective sequence classification facing sparse data. We use the BERT (Bidirectional Encoder Representation from Transformers) as the word embedding method. Then, we integrate the BiLSTM (Bidirectional Long Short-Term Memory) and CNN (Convolutional Neural Network) with an attention mechanism for sequence classification. We evaluate our ensemble models with two datasets with the different baseline methods. The first dataset is from IMDB and contains 50,000 movie reviews, labeled with two sentiment classes. The second dataset is the Toxic Comment Dataset with more than 150,000 comments for six classes. The experimental results show that our proposed method provides an accurate, reliable, and effective solution for sequence data classification.},
 title = {Ensemble BERT-BiLSTM-CNN Model for Sequence Classification},
 year = {2021}
}