A novel dropout mechanism with label extension schema toward text emotion classification
Article
Li, Zongxi, Li, Xianming, Xie, Haoran, Wang, Fu Lee, Leng, Mingming, Li, Qing and Tao, Xiaohui. 2023. "A novel dropout mechanism with label extension schema toward text emotion classification." Information Processing and Management. 60 (2). https://doi.org/10.1016/j.ipm.2022.103173
| Article Title | A novel dropout mechanism with label extension schema toward text emotion classification |
|---|---|
| ERA Journal ID | 17904 |
| Article Category | Article |
| Authors | Li, Zongxi, Li, Xianming, Xie, Haoran, Wang, Fu Lee, Leng, Mingming, Li, Qing and Tao, Xiaohui |
| Journal Title | Information Processing and Management |
| Journal Citation | 60 (2) |
| Article Number | 103173 |
| Number of Pages | 20 |
| Year | 2023 |
| Place of Publication | United Kingdom |
| ISSN | 0306-4573 |
| 1873-5371 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.ipm.2022.103173 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0306457322002746 |
| Abstract | Researchers have been aware that emotion is not one-hot encoded in emotion-relevant classification tasks, and multiple emotions can coexist in a given sentence. Recently, several works have focused on leveraging a distribution label or a grayscale label of emotions in the classification model, which can enhance the one-hot label with additional information, such as the intensity of other emotions and the correlation between emotions. Such an approach has been proven effective in alleviating the overfitting problem and improving the model robustness by introducing a distribution learning component in the objective function. However, the effect of distribution learning cannot be fully unfolded as it can reduce the model's discriminative ability within similar emotion categories. For example, Sad and Fear are both negative emotions. To address such a problem, we proposed a novel emotion extension scheme in the prior work (Li, Chen, Xie, Li, and Tao, 2021). The prior work incorporated fine-grained emotion concepts to build an extended label space, where a mapping function between coarse-grained emotion categories and fine-grained emotion concepts was identified. For example, sentences labeled Joy can convey various emotions such as enjoy, free, and leisure. The model can further benefit from the extended space by extracting dependency within fine-grained emotions when yielding predictions in the original label space. The prior work has shown that it is more apt to apply distribution learning in the extended label space than in the original space. A novel sparse connection method, i.e., Leaky Dropout, is proposed in this paper to refine the dependency-extraction step, which further improves the classification performance. In addition to the multiclass emotion classification task, we extensively experimented on sentiment analysis and multilabel emotion prediction tasks to investigate the effectiveness and generality of the label extension schema. |
| Keywords | Leaky dropout; Emotion classification; Sentiment analysis; Label extension; Distribution learning |
| Byline Affiliations | Hong Kong Metropolitan University, China |
| Ant Group, China | |
| Lingnan University of Hong Kong, China | |
| Hong Kong Polytechnic University, China | |
| School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z2630/a-novel-dropout-mechanism-with-label-extension-schema-toward-text-emotion-classification
Download files
Published Version
| A novel dropout mechanism with label extension schema toward text emotion classification.pdf | ||
| License: CC BY-NC-ND 4.0 | ||
| File access level: Anyone | ||
89
total views40
total downloads10
views this month1
downloads this month