arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.04762cs.CLcs.LG
收藏

用于文本分类的双状态胶囊网络

Dual-State Capsule Networks for Text Classification

University of Moratuwa(莫拉图瓦大学)

Piyumal Demotte, Surangika Ranathunga

摘要:

基于上下文嵌入的文本分类系统对于许多低资源语言来说是不可行的选择。另一方面,最近推出的胶囊网络显示出与这些文本分类模型相当的性能。因此,它们可以被认为是一个可行的替代文本分类的语言,没有预先训练的上下文嵌入模型。然而,目前的胶囊网络依赖于空间模式,而不考虑文本的顺序特征。它们在捕获较长序列中的上下文级别信息方面也是次优的。本文提出了一种新的基于双状态胶囊(DS-Caps)网络的文本分类技术,该技术经过优化以缓解这些问题。两种状态,即句子级和单词级,与胶囊层集成,以捕获更深层次的上下文级信息,用于语言建模。利用状态层次的上下文层次信息,对胶囊间的动态路由过程进行了优化。DS-Caps网络在多个数据集上的性能优于现有的胶囊网络架构,特别是对于具有较长文本序列的任务。我们还证明了DS-Caps在低资源语言的文本分类中的优越性。

英文摘要:

Text classification systems based on contextual embeddings are not viable options for many of the low resource languages. On the other hand, recently introduced capsule networks have shown performance in par with these text classification models. Thus, they could be considered as a viable alternative for text classification for languages that do not have pre-trained contextual embedding models. However, current capsule networks depend upon spatial patterns without considering the sequential features of the text. They are also sub-optimal in capturing the context-level information in longer sequences. This paper presents a novel Dual-State Capsule (DS-Caps) network-based technique for text classification, which is optimized to mitigate these issues. Two varieties of states, namely sentence-level and word-level, are integrated with capsule layers to capture deeper context-level information for language modeling. The dynamic routing process among capsules was also optimized using the context-level information obtained through sentence-level states. The DS-Caps networks outperform the existing capsule network architectures for multiple datasets, particularly for tasks with longer sequences of text. We also demonstrate the superiority of DS-Caps in text classification for a low resource language.

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。

↑