End to end binarized neural networks for text classification

Show simple item record

dc.contributor.author Jain, Harshil
dc.contributor.author Agarwal, Akshat
dc.contributor.author Shridhar, Kumar
dc.contributor.author Kleyko, Denis
dc.date.accessioned 2020-10-23T15:17:44Z
dc.date.available 2020-10-23T15:17:44Z
dc.date.issued 2020-10
dc.identifier.citation Jain, Harshil; Agarwal, Akshat; Shridhar, Kumar; Kleyko, Denis, "End to end binarized neural networks for text classification", arXiv, Cornell University Library, DOI: arXiv:2010.05223, Oct. 2020. en_US
dc.identifier.uri https://arxiv.org/abs/2010.05223
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/5802
dc.description.abstract Deep neural networks have demonstrated their superior performance in almost every Natural Language Processing task, however, their increasing complexity raises concerns. In particular, these networks require high expenses on computational hardware, and training budget is a concern for many. Even for a trained network, the inference phase can be too demanding for resource-constrained devices, thus limiting its applicability. The state-of-the-art transformer models are a vivid example. Simplifying the computations performed by a network is one way of relaxing the complexity requirements. In this paper, we propose an end to end binarized neural network architecture for the intent classification task. In order to fully utilize the potential of end to end binarization, both input representations (vector embeddings of tokens statistics) and the classifier are binarized. We demonstrate the efficiency of such architecture on the intent classification of short texts over three datasets and for text classification with a larger dataset. The proposed architecture achieves comparable to the state-of-the-art results on standard intent classification datasets while utilizing ~ 20-40% lesser memory and training time. Furthermore, the individual components of the architecture, such as binarized vector embeddings of documents or binarized classifiers, can be used separately with not necessarily fully binary architectures.
dc.description.statementofresponsibility by Harshil Jain, Akshat Agarwal, Kumar Shridhar and Denis Kleyko
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.subject Machine Learning en_US
dc.title End to end binarized neural networks for text classification en_US
dc.type Pre-Print en_US
dc.relation.journal arXiv


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account