Graph convolutional network (GCN) has been successfully applied to capture global non-consecutive and long-distance semantic information for text classification. However, while GCN-based methods have shown promising results in offline evaluations, they commonly follow a seen-token-seen-document paradigm by constructing fixed document-token graph cannot make inferences on new documents. It is ch...

Abstract For short text classification, insufficient labeled data, data sparsity, and imbalanced classification have become three major challenges. this, we proposed multiple weak supervision, which can label unlabeled automatically. Different from prior work, the method generate probabilistic labels through conditional independent model. What’s more, experiments were conducted to verify effect...

Assigning predefined classes to natural language texts, based on their content, is a necessary component in many tasks organizations. This task carried out by classifying documents within set of categories using models and computational methods. Text representation for classification purposes has traditionally been performed vector space model due its good performance simplicity. Moreover, the ...

In most e-commerce platforms, product title classification is a crucial task. It can assist sellers listing an item in an appropriate category. At first glance, product title classification is merely an instance of text classification problems, which are well-studied in literature. However, product titles possess some properties very different from general documents. A title is usually a very s...

In recent years, production of text documents has seen an exponential growth, which is the reason why their proper classification seems necessary for better access. One of the main problems of classifying text documents is working in high-dimensional feature space. Feature Selection (FS) is one of the ways to reduce the number of text attributes. So, working with a great bulk of the feature spa...