https://scholars.lib.ntu.edu.tw/handle/123456789/629157
標題: | Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis | 作者: | Hsu, Ting Wei Chen, Chung Chi Huang, Hen Hsen HSIN-HSI CHEN |
公開日期: | 1-一月-2021 | 來源出版物: | EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings | 摘要: | 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. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126912679&partnerID=40&md5=31175a190ba43c9929c8f480a9273371 | ISBN: | 9781955917094 | SDG/關鍵字: | Motion estimation; Semantics; Data augmentation; Movement prediction; Performance; Price risks; Real-world; Replacement strategy; Semantic consistency; Semantic preservation; Sentiment analysis; Stock price; Sentiment analysis |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。