Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
5-2020
Abstract
Target-level sentiment classification aims at assigning sentiment polarities to opinion targets in a sentence, for which it is significantly more challenging to obtain large-scale labeled data than sentence/document-level sentiment classification due to the intricate contexts and relations of the target words. To address this challenge, we propose a novel semi-supervised approach to learn sentiment-aware representations from easily accessible unlabeled data specifically for the finegrained sentiment learning. This is very different from current popular semi-supervised solutions that use the unlabeled data via pretraining to generate generic representations for various types of downstream tasks. Particularly, we show for the first time that we can learn and detect some highly sentiment-discriminative neural units from the unsupervised pretrained model, termed neural sentiment units. Due to the discriminability, these sentiment units can be leveraged by downstream LSTM-based classifiers to generate sentiment-aware and context-dependent word representations to substantially improve their sentiment classification performance. Extensive empirical results on two benchmark datasets show that our approach (i) substantially outperforms state-of-the-art sentiment classifiers and (ii) achieves significantly better data efficiency.
Keywords
Discriminative neural sentiment units, Target-level sentiment analysis, Deep neural network
Discipline
Artificial Intelligence and Robotics
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 24th Pacific-Asia Conference, PAKDD 2020, Singapore, May 11-14
Volume
12085
First Page
798
Last Page
810
ISBN
9783030474355
Identifier
10.1007/978-3-030-47436-2_60
Publisher
Springer
City or Country
Singapore
Citation
ZHAO, Jingjing; YANG, Yao; PANG, Guansong; LV, Lei; SHANG, Hong; SUN, Zhongqian; and YANG, Wei.
Learning discriminative neural sentiment units for semi-supervised target-level sentiment classification. (2020). Proceedings of the 24th Pacific-Asia Conference, PAKDD 2020, Singapore, May 11-14. 12085, 798-810.
Available at: https://ink.library.smu.edu.sg/sis_research/7059
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.