HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text Categorization
HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text Categorization
复制标题
DOI：
10.18653/v1/d18-1093
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Kazuya Shimura;Jiyi Li;Fumiyo Fukumoto
中科院分区：
文献类型：
--
作者：
Kazuya Shimura;Jiyi Li;Fumiyo Fukumoto
我们主要研究短文本的多标签分类任务，并探索分类的层次结构（HS）。与现有的非层次平面模型相比，该方法利用预定义类别之间的层次关系来解决数据稀疏性问题。HS水平越低，分类效果越差。因为低层次的每个类别的训练数据数量要比高层次的少得多。我们提出了一种方法，利用卷积神经网络（CNN）的微调技术，有效地利用上层的数据来贡献下层的分类。使用两个基准数据集的结果表明，本文提出的基于层次微调的CNN （HFT-CNN）方法与最先进的基于CNN的方法具有竞争力。
We focus on the multi-label categorization task for short texts and explore the use of a hierarchical structure (HS) of categories. In contrast to the existing work using non-hierarchical flat model, the method leverages the hierarchical relations between the pre-defined categories to tackle the data sparsity problem. The lower the HS level, the less the categorization performance. Because the number of training data per category in a lower level is much smaller than that in an upper level. We propose an approach which can effectively utilize the data in the upper levels to contribute the categorization in the lower levels by applying the Convolutional Neural Network (CNN) with a fine-tuning technique. The results using two benchmark datasets show that proposed method, Hierarchical Fine-Tuning based CNN (HFT-CNN) is competitive with the state-of-the-art CNN based methods.