Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information

Ling Gan, Houyu Gong


Abstract
Tree-structured Long Short-Term Memory (Tree-LSTM) has been proved to be an effective method in the sentiment analysis task. It extracts structural information on text, and uses Long Short-Term Memory (LSTM) cell to prevent gradient vanish. However, though combining the LSTM cell, it is still a kind of model that extracts the structural information and almost not extracts serialization information. In this paper, we propose three new models in order to combine those two kinds of information: the structural information generated by the Constituency Tree-LSTM and the serialization information generated by Long-Short Term Memory neural network. Our experiments show that combining those two kinds of information can give contributes to the performance of the sentiment analysis task compared with the single Constituency Tree-LSTM model and the LSTM model.
Anthology ID:
I17-1034
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
336–341
Language:
URL:
https://aclanthology.org/I17-1034
DOI:
Bibkey:
Cite (ACL):
Ling Gan and Houyu Gong. 2017. Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 336–341, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information (Gan & Gong, IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-1034.pdf
Data
SST