Abstract
Internet memes emotion recognition is focused by many researchers. In this paper, we adopt BERT and ResNet for evaluation of detecting the emotions of Internet memes. We focus on solving the problem of data imbalance and data contains noise. We use RandAugment to enhance the data of the picture, and use Training Signal Annealing (TSA) to solve the impact of the imbalance of the label. At the same time, a new loss function is designed to ensure that the model is not affected by input noise which will improve the robustness of the model. We participated in sub-task a and our model based on BERT obtains 34.58% macro F1 score, ranking 10/32.- Anthology ID:
- 2020.semeval-1.145
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Editors:
- Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 1100–1105
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.145
- DOI:
- 10.18653/v1/2020.semeval-1.145
- Cite (ACL):
- Zhen Li, Yaojie Zhang, Bing Xu, and Tiejun Zhao. 2020. CN-HIT-MI.T at SemEval-2020 Task 8: Memotion Analysis Based on BERT. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1100–1105, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- CN-HIT-MI.T at SemEval-2020 Task 8: Memotion Analysis Based on BERT (Li et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.semeval-1.145.pdf