Semantic Simplification for Sentiment Classification

Xiaotong Jiang, Zhongqing Wang, Guodong Zhou


Abstract
Recent work on document-level sentiment classification has shown that the sentiment in the original text is often hard to capture, since the sentiment is usually either expressed implicitly or shifted due to the occurrences of negation and rhetorical words. To this end, we enhance the original text with a sentiment-driven simplified clause to intensify its sentiment. The simplified clause shares the same opinion with the original text but expresses the opinion much more simply. Meanwhile, we employ Abstract Meaning Representation (AMR) for generating simplified clauses, since AMR explicitly provides core semantic knowledge, and potentially offers core concepts and explicit structures of original texts. Empirical studies show the effectiveness of our proposed model over several strong baselines. The results also indicate the importance of simplified clauses for sentiment classification.
Anthology ID:
2022.emnlp-main.757
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11022–11032
Language:
URL:
https://aclanthology.org/2022.emnlp-main.757
DOI:
10.18653/v1/2022.emnlp-main.757
Bibkey:
Cite (ACL):
Xiaotong Jiang, Zhongqing Wang, and Guodong Zhou. 2022. Semantic Simplification for Sentiment Classification. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11022–11032, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Semantic Simplification for Sentiment Classification (Jiang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.757.pdf