Volltext-Downloads (blau) und Frontdoor-Views (grau)

Opinion Holder and Target Extraction based on the Induction of Verbal Categories

  • We present an approach for opinion role induction for verbal predicates. Our model rests on the assumption that opinion verbs can be divided into three different types where each type is associated with a characteristic mapping between semantic roles and opinion holders and targets. In several experiments, we demonstrate the relevance of those three categories for the task. We show that verbs can easily be categorized with semi-supervised graphbased clustering and some appropriate similarity metric. The seeds are obtained through linguistic diagnostics. We evaluate our approach against a new manually-compiled opinion role lexicon and perform in-context classification.

Export metadata

Additional Services

Share in Twitter Search Google Scholar


Author:Michael Wiegand, Josef RuppenhoferGND
Parent Title (English):Proceedings of the 19th Conference on Computational Language Learnung, Beijing China, July 30-31, 2015
Publisher:Association for Computational Linguistics
Document Type:Conference Proceeding
Year of first Publication:2015
Date of Publication (online):2016/09/01
GND Keyword:Automatische Sprachanalyse; Meinungsverb; Propositionale Einstellung
First Page:215
Last Page:225
DDC classes:400 Sprache / 410 Linguistik
Open Access?:ja
Licence (German):License LogoCreative Commons - Namensnennung-Nicht kommerziell-Keine Bearbeitung 3.0 Deutschland