Abstract
The tiled convolutional neural network (TCNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the TCNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled convolutional neural network (HTCNN) that applies a filter only on the words that appear in similar contexts and on their neighbouring words (a necessary step for preventing the loss of some n-grams). The experiments on the IMDB movie reviews dataset demonstrate the effectiveness of the HTCNN that has a higher level of performance of more than 3% and 1% respectively than both the convolutional neural network (CNN) and the TCNN. These results are confirmed by the SemEval-2017 dataset where the recall of the HTCNN model exceeds by more than six percentage points the recall of its simple variant, CNN.
Original language | English |
---|---|
Title of host publication | Proceedings of the 12th International Conference on Agents and Artificial Intelligence |
Editors | Ana Rocha, Luc Steels, Jaap van den Herik |
Pages | 506-513 |
Number of pages | 8 |
Volume | 2 |
DOIs | |
Publication status | Published - Feb 2020 |
Event | 12th International Conference on Agents and Artificial Intelligence - Valetta, Malta Duration: 22 Feb 2020 → 24 Feb 2020 http://www.icaart.org |
Conference
Conference | 12th International Conference on Agents and Artificial Intelligence |
---|---|
Abbreviated title | ICAART 2020 |
Country/Territory | Malta |
City | Valetta |
Period | 22/02/20 → 24/02/20 |
Internet address |
Keywords
- Hybrid Tiled Convolutional Neural Network
- Sentiment Analysis