Integrating semantic knowledge to tackle zero-shot text classification

File Description SizeFormat 
1903.12626v1.pdfAccepted version441.24 kBAdobe PDFView/Open
Title: Integrating semantic knowledge to tackle zero-shot text classification
Authors: Zhang, J
Lertvittayakumjorn, P
Guo, Y
Item Type: Conference Paper
Abstract: 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.
Date of Acceptance: 2-Jun-2019
URI: http://hdl.handle.net/10044/1/73762
Copyright Statement: © 2019 The Authors.
Conference Name: 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Keywords: cs.CL
cs.CL
cs.CL
cs.CL
Notes: Accepted NAACL-HLT 2019
Start Date: 2019-06-03
Finish Date: 2019-06-05
Conference Place: Minneapolis
Appears in Collections:Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons