Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN

TL;DR

This paper introduces KASM, a novel neural network model that enhances short text classification by integrating knowledge graphs and similarity matrix-based CNNs to address word ambiguity and data sparsity.

Contribution

The paper proposes a knowledge-powered attention mechanism combined with similarity matrix CNNs, incorporating knowledge graphs for improved semantic representation in short text classification.

Findings

KASM outperforms existing methods on five datasets.

Knowledge graph integration improves semantic understanding.

Attention mechanisms effectively identify important information.

Abstract

Short text is becoming more and more popular on the web, such as Chat Message, SMS and Product Reviews. Accurately classifying short text is an important and challenging task. A number of studies have difficulties in addressing this problem because of the word ambiguity and data sparsity. To address this issue, we propose a knowledge powered attention with similarity matrix based convolutional neural network (KASM) model, which can compute comprehensive information by utilizing the knowledge and deep neural network. We use knowledge graph (KG) to enrich the semantic representation of short text, specially, the information of parent-entity is introduced in our model. Meanwhile, we consider the word interaction in the literal-level between short text and the representation of label, and utilize similarity matrix based convolutional neural network (CNN) to extract it. For the purpose of measuring the importance of knowledge, we introduce the attention mechanisms to choose the important information. Experimental results on five standard datasets show that our model significantly outperforms state-of-the-art methods.