Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-19010
Publication type: Conference paper
Type of review: Peer review (publication)
Title: Towards integration of statistical hypothesis tests into deep neural networks
Authors : Aghaebrahimian, Ahmad
Cieliebak, Mark
et. al : No
DOI : 10.18653/v1/P19-1557
10.21256/zhaw-19010
Proceedings: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Pages : 5551
Pages to: 5557
Conference details: 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28 July - 2 August 2019
Issue Date: 2019
Publisher / Ed. Institution : Association for Computational Linguistics
ISBN: 978-1-950737-48-2
Language : English
Subject (DDC) : 410.285: Computational linguistics
Abstract: We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical hypothesis testing method is used to extract the most informative words for each given class. These words are used as a class description for more label-aware text classification. Intuition is to help the model to concentrate on more informative words rather than more frequent ones. The model leverages the use of label descriptions in addition to the input text to enhance text classification performance. Our method is entirely data-driven, has no dependency on other sources of information than the training data, and is adaptable to different classification problems by providing appropriate training data without major hyper-parameter tuning. We trained and tested our system on several publicly available datasets, where we managed to improve the state-of-the-art on one set with a high margin and to obtain competitive results on all other ones.
URI: https://digitalcollection.zhaw.ch/handle/11475/19010
Fulltext version : Published version
License (according to publishing contract) : CC BY 4.0: Attribution 4.0 International
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Appears in Collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
P19-1557.pdf276.2 kBAdobe PDFThumbnail
View/Open


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