TU Darmstadt / ULB / TUbiblio

Identifying Argumentative Discourse Structures in Persuasive Essays

Stab, Christian and Gurevych, Iryna
Moschitti, Alessandro and Pang, Bo and Daelemans, Walter (eds.) (2014):
Identifying Argumentative Discourse Structures in Persuasive Essays.
In: Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), Association for Computational Linguistics, Doha, Qatar, [Online-Edition: http://www.aclweb.org/anthology/D14-1006],
[Conference or Workshop Item]

Abstract

In this paper, we present a novel approach for identifying argumentative discourse structures in persuasive essays. The structure of argumentation consists of several components (i.e. claims and premises) that are connected with argumentative relations. We consider this task in two consecutive steps. First, we identify the components of arguments using multiclass classification. Second, we classify a pair of argument components as either support or non-support for identifying the structure of argumentative discourse. For both tasks, we evaluate several classifiers and propose novel feature sets including structural, lexical, syntactic and contextual features. In our experiments, we obtain a macro F1-score of 0.726 for identifying argument components and 0.722 for argumentative relations.

Item Type: Conference or Workshop Item
Erschienen: 2014
Editors: Moschitti, Alessandro and Pang, Bo and Daelemans, Walter
Creators: Stab, Christian and Gurevych, Iryna
Title: Identifying Argumentative Discourse Structures in Persuasive Essays
Language: English
Abstract:

In this paper, we present a novel approach for identifying argumentative discourse structures in persuasive essays. The structure of argumentation consists of several components (i.e. claims and premises) that are connected with argumentative relations. We consider this task in two consecutive steps. First, we identify the components of arguments using multiclass classification. Second, we classify a pair of argument components as either support or non-support for identifying the structure of argumentative discourse. For both tasks, we evaluate several classifiers and propose novel feature sets including structural, lexical, syntactic and contextual features. In our experiments, we obtain a macro F1-score of 0.726 for identifying argument components and 0.722 for argumentative relations.

Title of Book: Conference on Empirical Methods in Natural Language Processing (EMNLP 2014)
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_reviewed;UKP_p_WIKULU;UKP_p_WIWEB;UKP_p_DKPro;UKP_s_DKPro_Core;UKP_s_DKPro_Lab;UKP_a_ArMin
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Doha, Qatar
Date Deposited: 31 Dec 2016 14:29
Official URL: http://www.aclweb.org/anthology/D14-1006
Identification Number: TUD-CS-2014-0882
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item