A pilot study for automatic semantic role labeling in a Dutch corpus

Abstract

We present an approach to automatic semantic role labeling (SRL) carried out in the context of the D-coi project. Although there has been an increasing interest in automatic SRL in recent years, previous research has focused mainly on English. Adapting earlier research to the Dutch situation poses an interesting challenge especially because there is no semantically annotated Dutch corpus available that can be used as training data. Our automatic SRL approach consists of three steps: bootstrapping from an unannotated corpus with a rulebased tagger developed for this purpose, manual correction and training a machine learning system on the manually corrected data. The input data for our SRL approach consists of Dutch sentences from the D-COI corpus, syntactically annotated by the Dutch dependency parser Alpino.