Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach

Bibtex

Cite as text

						@Select Types{,
							 
							 
							 
							 
							 
							Journal   = "Band-1",
							 Title= "Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach", 
							Author= "Thiemo Wambsganss, Nikolaos Molyndris, Matthias Söllner", 
							Doi= "https://doi.org/10.30844/wi_2020_c9-wambsganss", 
							 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.

", 
							 Keywords= "Argumentation Mining, Argument Identification, Transfer Learning, Natural Language Processing", 
							}
					
Thiemo Wambsganss, Nikolaos Molyndris, Matthias Söllner: Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach. Online: https://doi.org/10.30844/wi_2020_c9-wambsganss (Abgerufen 20.08.22)

Abstract

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.

Keywords

Schlüsselwörter

Argumentation Mining, Argument Identification, Transfer Learning, Natural Language Processing

References

Referenzen

Leider ist der Eintrag nur auf Amerikanisches Englisch verfügbar.

Most viewed articles

Meist angesehene Beiträge

GITO events | library.gito