Graph-based clustering of synonym senses for German particle verbs

Abstract

In this paper, we address the automatic induction of synonym paraphrases for the empirically challenging class of German particle verbs. Similarly to Cocos and Callison-Burch (2016), we incorporate a graph-based clustering approach for word sense discrimination into an existing paraphrase extraction system, (i) to improve the precision of synonym identification and ranking, and (ii) to enlarge the diversity of synonym senses. Our approach significantly improves over the standard system, but does not outperform an extended baseline integrating a simple distributional similarity measure.