TU Darmstadt / ULB / TUbiblio

Cross-topic Argument Mining from Heterogeneous Sources

Stab, Christian and Miller, Tristan and Schiller, Benjamin and Rai, Pranav and Gurevych, Iryna :
Cross-topic Argument Mining from Heterogeneous Sources.
[Online-Edition: http://aclweb.org/anthology/D18-1402]
In: The 2018 Conference on Empirical Methods in Natural Language Processing, 31.10.2018--04.11.2018, Brussels, Belgium. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
[Conference or Workshop Item] , (2018)

Official URL: http://aclweb.org/anthology/D18-1402

Abstract

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. We show that integrating topic information into bidirectional long short-term memory networks outperforms vanilla BiLSTMs by more than 3 percentage points in F1 in two- and three-label cross-topic settings. We also show that these results can be further improved by leveraging additional data for topic relevance using multi-task learning.

Item Type: Conference or Workshop Item
Erschienen: 2018
Creators: Stab, Christian and Miller, Tristan and Schiller, Benjamin and Rai, Pranav and Gurevych, Iryna
Title: Cross-topic Argument Mining from Heterogeneous Sources
Language: English
Abstract:

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. We show that integrating topic information into bidirectional long short-term memory networks outperforms vanilla BiLSTMs by more than 3 percentage points in F1 in two- and three-label cross-topic settings. We also show that these results can be further improved by leveraging additional data for topic relevance using multi-task learning.

Title of Book: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Volume: Long Papers
Uncontrolled Keywords: UKP_p_ArgumenText, UKP_a_ArMin
Divisions: Department of Computer Science
Department of Computer Science > Ubiquitous Knowledge Processing
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Event Title: The 2018 Conference on Empirical Methods in Natural Language Processing
Event Location: Brussels, Belgium
Event Dates: 31.10.2018--04.11.2018
Date Deposited: 08 Mar 2018 15:30
Official URL: http://aclweb.org/anthology/D18-1402
Identification Number: TUD-CS-2018-0052
Related URLs:
Projects: ArgumenText
Export:

Optionen (nur für Redakteure)

View Item View Item