ZERO SHOT LEARNING FOR TEXT CLASSIFICATION.

ZERO SHOT LEARNING FOR TEXT CLASSIFICATION.
Author(s):
Romika manhas, Dr. Simmi Dutta, Dr. Jyoti Kumar Mahajan
Keywords:
zero shot learning, zero shot text classification, semantic embeddings, BERT, knowledge graphs.
Abstract
Zero shot learning aims at solving the problem of object classification where we have no training examples as insufficient and uneven datasets for emerging classes is becoming a challenging issue monotonously. Zero shot text classification is an approach where we use zero shot learning to make models which are capable of categorizing the text documents which it has not seen during the testing phase. In this paper we will be giving a brief idea about zero shot learning and text classification with the different state-of- art methods which has been used for zero shot text classification problem which includes neural network with embeddings, semantic embeddings, using knowledge graphs etc.In addition we have applied distil BERT -a pretrained model, for seen classes and the results for the same has been discussed.
Article Details
Unique Paper ID: 157586 Publication Volume & Issue: Volume 9, Issue 7 Page(s): 601 - 603
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org