Attentive Representation Learning with Adversarial Training for Short Text Clustering

Abstract

Short text clustering has far-reaching effects on semantic analysis, showing its importance for multiple applications such as corpus summarization and information retrieval. However, it inevitably encounters the severe sparsity of short text representations, making the previous clustering approaches still far from satisfactory. In this paper, we present a novel attentive representation learning model for shot text clustering, wherein cluster-level attention is proposed to capture the correlations between text representations and cluster representations. Relying on this, the representation learning and clustering for short texts are seamlessly integrated into a unified model. To further ensure robust model training for short texts, we apply adversarial training to the unsupervised clustering setting, by injecting perturbations into the cluster representations. The model parameters and perturbations are optimized alternately through a minimax game. Extensive experiments on four real-world short text datasets demonstrate the superiority of the proposed model over several strong competitors, verifying that robust adversarial training yields substantial performance gains.

arXiv comment14pages, to appear in IEEE TKDE

References in corpus (9)

• Distributed Representations of Words and Phrases and their Compositionality
• Auto-Encoding Variational Bayes
• Self-Attention Generative Adversarial Networks
• Pre-trained Models for Natural Language Processing: A Survey
• Adversarial Personalized Ranking for Recommendation
• Distributional Smoothing with Virtual Adversarial Training
• Self-Taught Convolutional Neural Networks for Short Text Clustering
• Deep Defense: Training DNNs with Improved Adversarial Robustness
• A Grid Based Adversarial Clustering Algorithm