“PageRank” for Argument Relevance

verfasst von

Henning Wachsmuth, Benno Stein, Yamen Ajjour

Abstract

Future search engines are expected to deliver pro and con arguments in response to queries on controversial topics. While argument mining is now in the focus of research, the question of how to retrieve the relevant arguments remains open. This paper proposes a radical model to assess relevance objectively at web scale: The relevance of an argument's conclusion is decided by what other arguments reuse it as a premise. We build an argument graph for this model that we analyze with a recursive weighting scheme, adapting key ideas of PageRank. In experiments on a large ground-truth argument graph, the resulting relevance scores correlate with human average judgments. We outline what natural language challenges must be faced at web scale in order to stepwise bring argument relevance to web search engines.

Externe Organisation(en)

Bauhaus-Universität Weimar

Typ

Aufsatz in Konferenzband

Seiten

1117-1127

Anzahl der Seiten

11

Publikationsdatum

04.2017

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Linguistik und Sprache, Sprache und Linguistik

Elektronische Version(en)

https://doi.org/10.18653/v1/e17-1105 (Zugang: Offen)
http://aclweb.org/anthology/E17-1105 (Zugang: Unbekannt)