“What does my classifier learn?”
| dc.contributor.author | Winkler, Jonas Paul | |
| dc.contributor.author | Vogelsang, Andreas | |
| dc.date.accessioned | 2018-05-15T09:07:26Z | |
| dc.date.available | 2018-05-15T09:07:26Z | |
| dc.date.issued | 2017 | |
| dc.description.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. | en |
| dc.identifier.isbn | 978-3-319-59569-6 | |
| dc.identifier.uri | https://depositonce.tu-berlin.de/handle/11303/7786 | |
| dc.identifier.uri | http://dx.doi.org/10.14279/depositonce-6964 | |
| dc.language.iso | en | en |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | en |
| dc.subject.ddc | 004 Datenverarbeitung; Informatik | de |
| dc.subject.other | visual feedback | en |
| dc.subject.other | neural networks | en |
| dc.subject.other | artificial intelligence | en |
| dc.subject.other | machine learning | en |
| dc.subject.other | natural language processing | en |
| dc.subject.other | explanations | en |
| dc.subject.other | requirements engineering | en |
| dc.title | “What does my classifier learn?” | en |
| dc.title.subtitle | A visual approach to understanding natural language text classifiers | en |
| dc.type | Conference Object | en |
| dc.type.version | acceptedVersion | en |
| dcterms.bibliographicCitation.doi | 10.1007/978-3-319-59569-6_55 | en |
| dcterms.bibliographicCitation.originalpublishername | Springer | en |
| dcterms.bibliographicCitation.originalpublisherplace | Cham | en |
| dcterms.bibliographicCitation.pageend | 479 | en |
| dcterms.bibliographicCitation.pagestart | 468 | en |
| dcterms.bibliographicCitation.proceedingstitle | Natural Language Processing and Information Systems. NLDB 2017 | en |
| dcterms.bibliographicCitation.volume | 2017 | en |
| tub.accessrights.dnb | free | en |
| tub.affiliation | Fak. 4 Elektrotechnik und Informatik::Inst. Telekommunikationssysteme::FG IT-basierte Fahrzeuginnovationen | de |
| tub.affiliation.faculty | Fak. 4 Elektrotechnik und Informatik | de |
| tub.affiliation.group | FG IT-basierte Fahrzeuginnovationen | de |
| tub.affiliation.institute | Inst. Telekommunikationssysteme | de |
| tub.publisher.universityorinstitution | Technische Universität Berlin | en |
| tub.series.issuenumber | 10260 | en |
| tub.series.name | Lecture Notes in Computer Science | en |