Combining Knowledge with Deep Convolutional Neural Networks for Short Text Classification
Combining Knowledge with Deep Convolutional Neural Networks for Short Text Classification
复制标题
DOI：
10.24963/ijcai.2017/406
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Jin Wang;Zhongyuan Wang;Dawei Zhang;Jun Yan
中科院分区：
文献类型：
--
作者：
Jin Wang;Zhongyuan Wang;Dawei Zhang;Jun Yan
文本分类fi是自然语言处理应用中的一项基本任务。大多数现有的工作依赖于显式或隐式文本表示来解决这一问题。虽然这些技术对句子很有效，但由于短文本简短而稀疏，它们不容易应用于短文本。在本文中，我们提出了一种基于卷积神经网络的框架，它将短文本的显式表示和隐式表示相结合，用于Classifi阳离子。我们fi首先使用大型分类知识库将短文本概念化为一组相关概念。然后，我们通过将单词和相关概念合并到预先训练的单词向量上来获得短文本的嵌入。我们进一步将字符级别的特征引入到我们的模型中，以捕获fi细粒度的子词信息。在fiVe常用数据集上的实验结果表明，我们提出的方法在性能上明显优于最新的fi方法。
Text classification is a fundamental task in NLP applications. Most existing work relied on either explicit or implicit text representation to address this problem. While these techniques work well for sentences, they can not easily be applied to short text because of its shortness and sparsity. In this paper, we propose a framework based on convolutional neural networks that combines explicit and implicit representations of short text for classification. We first conceptualize a short text as a set of relevant concepts using a large taxonomy knowledge base. We then obtain the embedding of short text by coalescing the words and relevant concepts on top of pre-trained word vectors. We further incorporate character level features into our model to capture fine-grained subword information. Experimental results on five commonly used datasets show that our proposed method significantly out-performs state-of-the-art methods.