A Novel Teacher-Student Network for Sentiment Classification

DOI

10.2991/aiie-16.2016.118How to use a DOI?

Keywords

sentiment classification; knowledge transfer; deep learning; RNN

Abstract

Compared with traditional text classification, many sentiments online such as product reviews are not standard, which are concise with clear standpoints. Researchers on sentiment classification face tremendous challenges. Although various sentiment analysis systems are available, they have many operation restrictions and are still far from perfect. In this paper, we propose a novel approach, Teacher-Student Network (TSN), for automatically classifying the sentiment of reviews. Teacher-Student Network Model is composed of one teacher network and one student network. Teacher network is a Na‹ve Bayes model. Student network is deep neural networks model. Our approach can transfer knowledge between different models and requires less training data. Experimental results on different domain datasets show that when we employ full training data, our model can achieve similar performance to RNN(Recurrent Neural Network) model andwhen we reduce training data, our model achieve better performance than RNN.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huajie Chen
AU  - Eric Ke Wang
AU  - Feng Li
AU  - Wenli Yu
PY  - 2016/11
DA  - 2016/11
TI  - A Novel Teacher-Student Network for Sentiment Classification
BT  - Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
PB  - Atlantis Press
SP  - 507
EP  - 512
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-16.2016.118
DO  - 10.2991/aiie-16.2016.118
ID  - Chen2016/11
ER  -