We introduce two Bayesian models for unsupervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The first model induces these clusterings independently for each predicate, exploiting the Chinese Restaurant Process (CRP) as a prior. In a more refined hierarchical model, we inject the intuition that the clusterings are similar across different predicates, even though they are not necessarily identical. This intuition is encoded as a distance-dependent CRP with a distance between two syntactic signatures indicating how likely they are to correspond to a single semantic role. These distances are automatically induced within the model and shared across predicates. Both models achieve state-of-the-art results when evaluated on PropBank, with the coupled model consistently outperforming the factored counterpart in all experimental set-ups. 1

We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervised induction of semantic roles from sentences annotated with automatically-predicted syntactic dependency representations and use a stateof-the-art generative Bayesian non-parametric model. At inference time, instead of only seeking the model which explains the monolingual data available for each language, we regularize the objective by introducing a soft constraint penalizing for disagreement in argument labeling on aligned sentences. We propose a simple approximate learning algorithm for our set-up which results in efficient inference. When applied to German-English parallel data, our method obtains a substantial improvement over a model trained without using the agreement signal, when both are tested on non-parallel sentences. 1

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, 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. 1