.png){kind=icon}
返回
Generative Multi-Task Learning for Text Classification
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.2991337.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. In this paper, a generative multi-task learning (MTL) approach for text classification and categorization is proposed, which is composed of a shared encoder, a multi-label classification decoder and a hierarchical categorization decoder. In the two decoders, a label-order-independent multi-label classification loss function and a hierarchical structure mask matrix are introduced. Experiments conducted on the real-world public security dataset show that the proposed approach has obvious advantages over the baseline approaches and can enhance the semantic association between the results of the classification and categorization tasks.
Keyword:
Generative model
hierarchical classification
multi-label classification
multi-task learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Definitive evidence that a single N-glycan among three glycans on inducible costimulator is required for proper protein trafficking and ligand binding明确的证据表明，在可诱导的共刺激物上的三个聚糖中，单个N-聚糖对于适当的蛋白质运输和配体结合是必需的
PREAI
分享收藏Effect of seepage conditions on chemical attenuation of arsenic by soils across an abandoned mine site.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏ML-KNN: A lazy learning approach to multi-label leamingMl-knn: 一种多标签学习的懒惰学习方法PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏分享收藏分享收藏
查看更多内容