The frame-semantic parsing task is challenging for supervised techniques, even for those few languages where relatively large amounts of labeled data are available. In this preliminary work, we consider unsupervised induction of frame-semantic representations. An existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, EACL 2012) is extended to jointly induce semantic frames and their roles. We evaluate the model performance both quantitatively and qualitatively by comparing the induced representation against FrameNet annotations.
|Title of host publication||Proceedings of the NAACL-HLT 2012 Workshop on Inducing Linguistic Structure|
|Place of Publication||Montreal, Canada|
|Number of pages||7|
|Publication status||Published - 1 Jun 2012|