Attentive Representation Learning With Adversarial Training for Short Text Clustering

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 representations, making previous approaches still far from satisfactory. In this paper, we present a novel attentive representation learning model shot clustering, wherein cluster-level attention is proposed to capture correlations between representations cluster representations. Relying this, texts are seamlessly integrated into unified model. To further ensure robust training texts, apply adversarial unsupervised setting, by injecting perturbations The parameters optimized alternately through minimax game. Extensive experiments four real-world datasets demonstrate superiority over several strong competitors, verifying that yields substantial performance gains.