Date
2020Subject
004 Data processing and computer science 300 Social sciences ArgumentIdentifikationTransferLernenNatürlichsprachiges SystemMetadata
Show full item record
Konferenzveröffentlichung
Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach
Abstract
Argument identification is the fundamental block of every Argumentation Mining pipeline, which in turn is a young upcoming field with multiple applications ranging from strategy support to opinion mining and news fact-checking. We developed a model, which is tackling the two biggest practical and academic challenges of the research field today. First, it addresses the lack of corpus-agnostic models and, second, it tackles the problem of human-labor-intensive NLP models being costly to develop. We do that by suggesting and implementing an easy-to-use solution that utilizes the latest advancements in natural language Transfer Learning. The result is a two-fold contribution: A system that delivers state-of-the-art results in multiple corpora and opens up a new way of academic advancement of the field through Transfer Learning. Additionally, it provides the architecture for an easy-to-use tool that can be used for practical applications without the need for domain-specific knowledge.
Citation
In: Gronau, Norbert; Heine, Moreen; Krasnova, Hanna; Pousttchi, Key (Hrsg.): Entwicklungen, Chancen und Herausforderungen der Digitalisierung. Band 1: Proceedings der 15. Internationalen Tagung Wirtschaftsinformatik 2020. GITO Verlag: Berlin 2020, S. 341-356; ISBN 978-3-95545-335-0Citation
@inproceedings{doi:10.17170/kobra-202010231995,
author={Wambsganss, Thiemo and Molyndris, Nikolaos and Söllner, Matthias},
title={Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach},
booktitle={Entwicklungen, Chancen und Herausforderungen der Digitalisierung. Band 1: Proceedings der 15. Internationalen Tagung Wirtschaftsinformatik 2020},
year={2020}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2020$n2020 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/11899 3000 Wambsganss, Thiemo 3010 Molyndris, Nikolaos 3010 Söllner, Matthias 4000 Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach / Wambsganss, Thiemo 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/11899=x R 4204 \$dKonferenzveröffentlichung 4170 5550 {{Argument}} 5550 {{Identifikation}} 5550 {{Transfer}} 5550 {{Lernen}} 5550 {{Natürlichsprachiges System}} 7136 ##0##http://hdl.handle.net/123456789/11899
2020-10-26T14:36:13Z 2020-10-26T14:36:13Z 2020 doi:10.17170/kobra-202010231995 http://hdl.handle.net/123456789/11899 eng GITO Verlag Urheberrechtlich geschützt https://rightsstatements.org/page/InC/1.0/ argumentation mining argument identification transfer learning natural language processing 004 300 Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach Konferenzveröffentlichung Argument identification is the fundamental block of every Argumentation Mining pipeline, which in turn is a young upcoming field with multiple applications ranging from strategy support to opinion mining and news fact-checking. We developed a model, which is tackling the two biggest practical and academic challenges of the research field today. First, it addresses the lack of corpus-agnostic models and, second, it tackles the problem of human-labor-intensive NLP models being costly to develop. We do that by suggesting and implementing an easy-to-use solution that utilizes the latest advancements in natural language Transfer Learning. The result is a two-fold contribution: A system that delivers state-of-the-art results in multiple corpora and opens up a new way of academic advancement of the field through Transfer Learning. Additionally, it provides the architecture for an easy-to-use tool that can be used for practical applications without the need for domain-specific knowledge. open access Wambsganss, Thiemo Molyndris, Nikolaos Söllner, Matthias Berlin doi:10.30844/wi_2020_c9-wambsganss Argument Identifikation Transfer Lernen Natürlichsprachiges System publishedVersion 2020-03 Potsdam Entwicklungen, Chancen und Herausforderungen der Digitalisierung. Band 1: Proceedings der 15. Internationalen Tagung Wirtschaftsinformatik 2020 Gronau, Norbert Heine, Moreen Krasnova, Hanna Pousttchi, Key ISBN 978-3-95545-335-0 341-356 false 15. Internationalen Tagung Wirtschaftsinformatik 2020
The following license files are associated with this item:
Urheberrechtlich geschützt