Dissecting Content and Context in Argumentative Relation Analysis

Juri Opitz, Anette Frank


Abstract
When assessing relations between argumentative units (e.g., support or attack), computational systems often exploit disclosing indicators or markers that are not part of elementary argumentative units (EAUs) themselves, but are gained from their context (position in paragraph, preceding tokens, etc.). We show that this dependency is much stronger than previously assumed. In fact, we show that by completely masking the EAU text spans and only feeding information from their context, a competitive system may function even better. We argue that an argument analysis system that relies more on discourse context than the argument’s content is unsafe, since it can easily be tricked. To alleviate this issue, we separate argumentative units from their context such that the system is forced to model and rely on an EAU’s content. We show that the resulting classification system is more robust, and argue that such models are better suited for predicting argumentative relations across documents.
Anthology ID:
W19-4503
Volume:
Proceedings of the 6th Workshop on Argument Mining
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Benno Stein, Henning Wachsmuth
Venue:
ArgMining
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
25–34
Language:
URL:
https://aclanthology.org/W19-4503
DOI:
10.18653/v1/W19-4503
Bibkey:
Cite (ACL):
Juri Opitz and Anette Frank. 2019. Dissecting Content and Context in Argumentative Relation Analysis. In Proceedings of the 6th Workshop on Argument Mining, pages 25–34, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Dissecting Content and Context in Argumentative Relation Analysis (Opitz & Frank, ArgMining 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4503.pdf