Please use this identifier to cite or link to this item:
Main Title: “What does my classifier learn?”
Subtitle: A visual approach to understanding natural language text classifiers
Author(s): Winkler, Jonas Paul
Vogelsang, Andreas
Type: Conference Object
Language Code: en
Abstract: Neural Networks have been utilized to solve various tasks such as image recognition, text classification, and machine translation and have achieved exceptional results in many of these tasks. However, understanding the inner workings of neural networks and explaining why a certain output is produced are no trivial tasks. Especially when dealing with text classification problems, an approach to explain network decisions may greatly increase the acceptance of neural network supported tools. In this paper, we present an approach to visualize reasons why a classification outcome is produced by convolutional neural networks by tracing back decisions made by the network. The approach is applied to various text classification problems, including our own requirements engineering related classification problem. We argue that by providing these explanations in neural network supported tools, users will use such tools with more confidence and also may allow the tool to do certain tasks automatically.
Issue Date: 2017
Date Available: 15-May-2018
DDC Class: 004 Datenverarbeitung; Informatik
Subject(s): visual feedback
neural networks
artificial intelligence
machine learning
natural language processing
requirements engineering
Proceedings Title: Natural Language Processing and Information Systems. NLDB 2017
Publisher: Springer
Publisher Place: Cham
Volume: 2017
Publisher DOI: 10.1007/978-3-319-59569-6_55
Page Start: 468
Page End: 479
Series: Lecture Notes in Computer Science
Series Number: 10260
ISBN: 978-3-319-59569-6
Appears in Collections:FG IT-basierte Fahrzeuginnovationen » Publications

Files in This Item:
File Description SizeFormat 
2017_winkler_vogelsang.pdf1.46 MBAdobe PDFView/Open

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