Abstract
this paper proposed a parallel-channel model to process the textual and visual information in memes and then analyze the sentiment polarity of memes. In the shared task of identifying and categorizing memes, we preprocess the dataset according to the language behaviors on social media. Then, we adapt and fine-tune the Bidirectional Encoder Representations from Transformers (BERT), and two types of convolutional neural network models (CNNs) were used to extract the features from the pictures. We applied an ensemble model that combined the BiLSTM, BIGRU, and Attention models to perform cross domain suggestion mining. The officially released results show that our system performs better than the baseline algorithm- Anthology ID:
- 2020.semeval-1.116
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 916–921
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.116
- DOI:
- 10.18653/v1/2020.semeval-1.116
- Cite (ACL):
- Li Yuan, Jin Wang, and Xuejie Zhang. 2020. YNU-HPCC at SemEval-2020 Task 8: Using a Parallel-Channel Model for Memotion Analysis. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 916–921, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- YNU-HPCC at SemEval-2020 Task 8: Using a Parallel-Channel Model for Memotion Analysis (Yuan et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2020.semeval-1.116.pdf
- Code
- YuanLi95/Semveal2020-Task8-emotion-analysis