Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis

Ting-Wei Hsu, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen


Abstract
Both the issues of data deficiencies and semantic consistency are important for data augmentation. Most of previous methods address the first issue, but ignore the second one. In the cases of aspect-based sentiment analysis, violation of the above issues may change the aspect and sentiment polarity. In this paper, we propose a semantics-preservation data augmentation approach by considering the importance of each word in a textual sequence according to the related aspects and sentiments. We then substitute the unimportant tokens with two replacement strategies without altering the aspect-level polarity. Our approach is evaluated on several publicly available sentiment analysis datasets and the real-world stock price/risk movement prediction scenarios. Experimental results show that our methodology achieves better performances in all datasets.
Anthology ID:
2021.emnlp-main.362
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4417–4422
Language:
URL:
https://aclanthology.org/2021.emnlp-main.362
DOI:
10.18653/v1/2021.emnlp-main.362
Bibkey:
Cite (ACL):
Ting-Wei Hsu, Chung-Chi Chen, Hen-Hsen Huang, and Hsin-Hsi Chen. 2021. Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4417–4422, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis (Hsu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.362.pdf
Software:
 2021.emnlp-main.362.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.362.mp4
Data
MAMSSSTSST-2StockNet