Abstract
Sentiment analysis is a classical problem of natural language processing. SemEval 2022 sets a problem on the structured sentiment analysis in task 10, which is also a study-worthy topic in research area. In this paper, we propose a method which can predict structured sentiment information on multiple languages with limited data. The ERNIE-M pretrained language model is employed as a lingual feature extractor which works well on multiple language processing, followed by a graph parser as a opinion extractor. The method can predict structured sentiment information with high interpretability. We apply data augmentation as the given datasets are so small. Furthermore, we use K-fold cross-validation and DeBERTaV3 pretrained model as extra English embedding generator to train multiple models as our ensemble strategies. Experimental results show that the proposed model has considerable performance on both monolingual and cross-lingual tasks.- Anthology ID:
- 2022.semeval-1.194
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1401–1405
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.194
- DOI:
- 10.18653/v1/2022.semeval-1.194
- Cite (ACL):
- Yalong Jia, Zhenghui Ou, and Yang Yang. 2022. SPDB Innovation Lab at SemEval-2022 Task 10: A Novel End-to-End Structured Sentiment Analysis Model based on the ERNIE-M. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1401–1405, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- SPDB Innovation Lab at SemEval-2022 Task 10: A Novel End-to-End Structured Sentiment Analysis Model based on the ERNIE-M (Jia et al., SemEval 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.semeval-1.194.pdf
- Data
- MPQA Opinion Corpus, MultiBooked