Integrating Semantic Knowledge to Tackle Zero-shot Text Classification
It addresses the problem of classifying text documents for unseen classes, which is a challenge in text classification due to insufficient training data, but the approach appears incremental as it builds on existing methods with semantic knowledge integration.
The paper tackles zero-shot text classification by integrating four types of semantic knowledge into a two-phase framework with data and feature augmentation, achieving the best overall accuracy compared to baselines and recent approaches in real-world text classification.
Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage, so-called zero-shot text classification, is therefore difficult and only limited previous works tackled this problem. In this paper, we propose a two-phase framework together with data augmentation and feature augmentation to solve this problem. Four kinds of semantic knowledge (word embeddings, class descriptions, class hierarchy, and a general knowledge graph) are incorporated into the proposed framework to deal with instances of unseen classes effectively. Experimental results show that each and the combination of the two phases achieve the best overall accuracy compared with baselines and recent approaches in classifying real-world texts under the zero-shot scenario.