SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity

Jaemin Kim, Yohan Na, Kangmin Kim, Sang-Rak Lee, Dong-Kyu Chae


Abstract
Recently, sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks. However, they neglect to evaluate the quality of their constructed sentiment representations; they just focus on improving the fine-tuning performance, which overshadows the representation quality. We argue that without guaranteeing the representation quality, their downstream performance can be highly dependent on the supervision of the fine-tuning data rather than representation quality. This problem would make them difficult to foray into other sentiment-related domains, especially where labeled data is scarce. We first propose Sentiment-guided Textual Similarity (SgTS), a novel metric for evaluating the quality of sentiment representations, which is designed based on the degree of equivalence in sentiment polarity between two sentences. We then propose SentiCSE, a novel Sentiment-aware Contrastive Sentence Embedding framework for constructing sentiment representations via combined word-level and sentence-level objectives, whose quality is guaranteed by SgTS. Qualitative and quantitative comparison with the previous sentiment-aware PLMs shows the superiority of our work. Our code is available at: https://github.com/nayohan/SentiCSE
Anthology ID:
2024.lrec-main.1280
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
14693–14704
Language:
URL:
https://aclanthology.org/2024.lrec-main.1280
DOI:
Bibkey:
Cite (ACL):
Jaemin Kim, Yohan Na, Kangmin Kim, Sang-Rak Lee, and Dong-Kyu Chae. 2024. SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14693–14704, Torino, Italia. ELRA and ICCL.
Cite (Informal):
SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity (Kim et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1280.pdf
Optional supplementary material:
 2024.lrec-main.1280.OptionalSupplementaryMaterial.pdf