Integrating Semantic Knowledge to Tackle Zero-shot Text Classification

Jingqing Zhang, Piyawat Lertvittayakumjorn, Yike Guo
2019 Proceedings of the 2019 Conference of the North  
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
more » ... ic 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 zeroshot scenario. * Piyawat Lertvittayakumjorn and Jingqing Zhang contributed equally to this project.
doi:10.18653/v1/n19-1108 dblp:conf/naacl/ZhangLG19 fatcat:pz4oubvlabdnzbbaufwmpdiyr4