tailieunhanh - Báo cáo khoa học: "Crosslingual Induction of Semantic Roles"

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. | Crosslingual Induction of Semantic Roles Ivan Titov Alexandre Klementiev Saarland University Saarbriicken Germany titov aklement @ Abstract 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 state-of-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 Introduction Learning in the context of multiple languages simultaneously has been shown to be beneficial to a number of NLP tasks from morphological analysis to syntactic parsing Kuhn 2004 Snyder and Barzilay 2010 McDonald et al. 2011 . The goal of this work is to show that parallel data is useful in unsupervised induction of shallow semantic representations. Semantic role labeling SRL Gildea and Juraf-sky 2002 involves predicting predicate argument structure . both the identification of arguments 647 and their assignment to underlying semantic roles. For example in the following sentences a IA .Peter I blamed A 1 Mary A2 for planning a theft . b A0Peter blamed A2planning a theft Alon Mary . c A I Mary I was blamed A2for planning a theft Aoby Peter the arguments Peter Mary and planning a theft of the predicate blame take the agent A0 patient A1 and reason A2 roles respectively. In this work we focus on .