A Soft Label Strategy for Target-Level Sentiment Classification

Da Yin, Xiao Liu, Xiuyu Wu, Baobao Chang


Abstract
In this paper, we propose a soft label approach to target-level sentiment classification task, in which a history-based soft labeling model is proposed to measure the possibility of a context word as an opinion word. We also apply a convolution layer to extract local active features, and introduce positional weights to take relative distance information into consideration. In addition, we obtain more informative target representation by training with context tokens together to make deeper interaction between target and context tokens. We conduct experiments on SemEval 2014 datasets and the experimental results show that our approach significantly outperforms previous models and gives state-of-the-art results on these datasets.
Anthology ID:
W19-1302
Volume:
Proceedings of the Tenth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
June
Year:
2019
Address:
Minneapolis, USA
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6–15
Language:
URL:
https://aclanthology.org/W19-1302
DOI:
10.18653/v1/W19-1302
Bibkey:
Cite (ACL):
Da Yin, Xiao Liu, Xiuyu Wu, and Baobao Chang. 2019. A Soft Label Strategy for Target-Level Sentiment Classification. In Proceedings of the Tenth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 6–15, Minneapolis, USA. Association for Computational Linguistics.
Cite (Informal):
A Soft Label Strategy for Target-Level Sentiment Classification (Yin et al., WASSA 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-1302.pdf