On the Impact of Reconstruction and Context for Argument Prediction in Natural Debate

Zlata Kikteva, Alexander Trautsch, Patrick Katzer, Mirko Oest, Steffen Herbold, Annette Hautli-Janisz

Abstract
Debate naturalness ranges on a scale from small, highly structured, and topically focused settings to larger, more spontaneous and less constrained environments. The more unconstrained a debate, the more spontaneous speakers act: they build on contextual knowledge and use anaphora or ellipses to construct their arguments. They also use rhetorical devices such as questions and imperatives to support or attack claims. In this paper, we study how the reconstruction of the actual debate contributions, i.e., utterances which contain pronouns, ellipses and fuzzy language, into full-fledged propositions which are interpretable without context impacts the prediction of argument relations and investigate the effect of incorporating contextual information for the task. We work with highly complex spontaneous debates with more than 10 speakers on a wide variety of topics. We find that in contrast to our initial hypothesis, reconstruction does not improve predictions and context only improves them when used in combination with propositions.
Anthology ID:
2023.argmining-1.10
Volume:
Proceedings of the 10th Workshop on Argument Mining
Month:
December
Year:
2023
Address:
Singapore
Editors:
Milad Alshomary, Chung-Chi Chen, Smaranda Muresan, Joonsuk Park, Julia Romberg
Venues:
ArgMining | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
100–106
Language:
URL:
https://aclanthology.org/2023.argmining-1.10
DOI:
10.18653/v1/2023.argmining-1.10
Bibkey:
Cite (ACL):
Zlata Kikteva, Alexander Trautsch, Patrick Katzer, Mirko Oest, Steffen Herbold, and Annette Hautli-Janisz. 2023. On the Impact of Reconstruction and Context for Argument Prediction in Natural Debate. In Proceedings of the 10th Workshop on Argument Mining, pages 100–106, Singapore. Association for Computational Linguistics.
Cite (Informal):
On the Impact of Reconstruction and Context for Argument Prediction in Natural Debate (Kikteva et al., ArgMining-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.argmining-1.10.pdf
PDF Search