In this paper we describe and evaluate an approach to linking readers’ comments to online news articles. For each comment that is linked based on its comment, we also determine whether the commenter agrees, disagrees or stays neutral with respect to what is stated in the article. We use similarity features to link comments to relevant article segments and Support Vector Regression models for assigning argument structure. Our results are compared to competing systems that took part in MultiLing OnForumS 2015 shared task, where we achieved best linking scores for English and second best for Italian.
|Titolo:||Sheffield-Trento System for Comment-to-Article Linking and Argument Structure Annotation in the Online News Domain.|
|Autori:||Aker, Ahmet; Celli, Fabio; Kurtic, Emina; Hepple, Mark; Gaizauskas, Robert|
|Anno di pubblicazione:||2015|
|Titolo del volume contenente il saggio:||Proceedings of MultiLing2015, in conjunction with SigDial 2015.|
|Citazione:||Sheffield-Trento System for Comment-to-Article Linking and Argument Structure Annotation in the Online News Domain / Aker, Ahmet; Celli, Fabio; Kurtic, Emina; Hepple, Mark; Gaizauskas, Robert. - ELETTRONICO. - (2015). ((Intervento presentato al convegno MultiLing2015 tenutosi a Prague nel 1 september 2015.|
|Appare nelle tipologie:||04.3 Poster presentato a convegno (Poster presented at Conference or Workshop)|