arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1710.07210cs.CL
收藏

文本分类中的多任务标签嵌入

Multi-Task Label Embedding for Text Classification

State Key Lab of Advanced Optical Communication System and Network(区域光纤通信网与新型光通信系统国家重点实验室)

Honglun Zhang, Liqiang Xiao, Wenqing Chen, Yongkun Wang, Yaohui Jin

摘要:

文本分类中的多任务学习利用相关任务之间的隐式相关性来提取共同特征并获得性能增益。然而,大多数以前的工作将每个任务的标签视为独立且无意义的独热向量,这导致潜在信息的丢失,并且使得这些模型难以联合学习三个或更多任务。本文提出了多任务标签嵌入技术,将文本分类中的标签转换为语义向量,从而将原始任务转化为向量匹配任务。我们实现了多任务标签嵌入的无监督,监督和半监督模型,所有这些模型都利用了任务之间的语义相关性,并且随着涉及更多任务,扩展和传输变得特别方便。在五个文本分类基准数据集上的大量实验表明,我们的模型可以有效地提高相关任务的性能,标签的语义表示和彼此的附加信息。

英文摘要:

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent and meaningless one-hot vectors, which cause a loss of potential information and makes it difficult for these models to jointly learn three or more tasks. In this paper, we propose Multi-Task Label Embedding to convert labels in text classification into semantic vectors, thereby turning the original tasks into vector matching tasks. We implement unsupervised, supervised and semi-supervised models of Multi-Task Label Embedding, all utilizing semantic correlations among tasks and making it particularly convenient to scale and transfer as more tasks are involved. Extensive experiments on five benchmark datasets for text classification show that our models can effectively improve performances of related tasks with semantic representations of labels and additional information from each other.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑