Same side stance classification

authored by

Benno Stein, Yamen Ajjour, Roxanne El Baff, Khalid Al-Khatib, Philipp Cimiano, Henning Wachsmuth

Abstract

This paper introduces the Same Side Stance Classification problem and reports on the outcome of a related shared task, which has been collocated with the Sixth Workshop on Argument Mining at the ACL 2019 in Florence.¹ We have proposed this task as a variant of the well-known stance classification task: Instead of predicting for a single argument whether it has a positive or negative stance towards a given topic, same side classification ‘merely’ involves the prediction of whether two given arguments share the same stance. The paper in hand provides the rationale for proposing this task, overviews important related work, describes the developed datasets, and reports on the results along with the main methods of the nine submitted systems. We draw conclusions from these results with respect to the suitability of the task as a proxy for measuring progress in the field of argument mining.

External Organisation(s)

Bauhaus-Universität Weimar
Bielefeld University
Paderborn University

Type

Conference article

Journal

CEUR Workshop Proceedings

Volume

2921

Pages

1-7

No. of pages

7

ISSN

1613-0073

Publication date

2021

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Computer Science(all)

Electronic version(s)

https://ceur-ws.org/Vol-2921/overview.pdf (Access: Open)