arXiv 1906.048982019-06-09cs.IRcs.LGstat.ML

基于层次分类和注意图的RCNN大规模多标签文本分类

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University（北京航空航天大学大数据与脑计算高精尖创新中心）；State Key Laboratory of Software Development Environment, Beihang University（北京航空航天大学软件开发环境国家重点实验室）；College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；University of Pennsylvania（宾夕法尼亚大学）；National Computer Network Emergency Response Technical Team/Coordination Center of China（国家计算机网络应急技术处理协调中心）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）

Hao Peng, Jianxin Li, Qiran Gong, Senzhang Wang, Lifang He, Bo Li, Lihong Wang, Philip S. Yu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

CNN、RNN、GCN和CapsNets在表示学习方面表现出了重要的见解，并广泛用于各种文本挖掘任务，如大规模多标签文本分类。然而，大多数现有的多标签文本分类的深度模型考虑非连续和长距离语义或顺序语义，但如何考虑这两个连贯的研究较少。此外，现有的方法大多将输出标签视为独立的方法，但忽略了它们之间的层次关系，导致有用的语义信息丢失。在本文中，我们提出了一种新的分层分类意识和注意力图胶囊循环CNN框架，用于大规模多标签文本分类。具体来说，我们首先建议每个文件的词序保留图形的话，并规范化为相应的词矩阵表示，保留了非连续的，长距离和本地顺序语义。然后将单词矩阵输入到所提出的注意力图胶囊递归CNN中，以更有效地学习语义特征。为了利用类标签之间的层次关系，我们提出了一种层次分类嵌入方法来学习它们的表示，并定义了一种新的加权余量损失，通过将标签表示相似性。在三个数据集上的广泛评估表明，与最先进的方法相比，我们的模型显着提高了大规模多标签文本分类的性能。

英文摘要：

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics, but how to consider them both coherently is less studied. In addition, most existing methods treat output labels as independent methods, but ignore the hierarchical relations among them, leading to useful semantic information loss. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding words-matrix representation which preserves both the non-consecutive, long-distance and local sequential semantics. Then the words-matrix is input to the proposed attentional graph capsule recurrent CNNs for more effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.

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。