Name
Abstract | ||
|---|---|---|
Weakly-supervised text classification aims to train predictive models with unlabeled texts and a few representative words of classes, referred to as category words, rather than labeled texts. These weak supervisions are much more cheaper and easy to collect in real-world scenarios. To resolve this task, we propose a novel deep classification model, namely Weakly-supervised Text Classification with Wasserstein Barycenter Regularization (WTC-WBR). Specifically, we initialize the pseudo-labels of texts by using the category word occurrences, and formulate a weakly self-training framework to iteratively update the weakly-supervised targets by combining the pseudo-labels with the sharpened predictions. Most importantly, we suggest a Wasserstein barycenter regularization with the weakly-supervised targets on the deep feature space. The intuition is that the texts tend to be close to the corresponding Wasserstein barycenter indicated by weakly-supervised targets. Another benefit is that the regularization can capture the geometric information of deep feature space to boost the discriminative power of deep features. Experimental results demonstrate that WTC-WBR outperforms the existing weakly-supervised baselines, and achieves comparable performance to semi-supervised and supervised baselines. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.24963/ijcai.2022/468 | European Conference on Artificial Intelligence |
Keywords | DocType | Citations |
Machine Learning: Classification,Machine Learning: Weakly Supervised Learning,Natural Language Processing: Text Classification | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jihong OuYang | 1 | 94 | 15.66 |
| Yiming Wang | 2 | 0 | 0.34 |
| Ximing Li | 3 | 0 | 0.34 |
| Changchun Li | 4 | 0 | 1.01 |