Paper: Crosslingual Induction of Semantic Roles

ACL ID P12-1068
Title Crosslingual Induction of Semantic Roles
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012

We argue that multilingual parallel data pro- vides a valuable source of indirect supervision for induction of shallow semantic representa- tions. Specifically, we consider unsupervised induction of semantic roles from sentences an- notated 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 mono- lingual data available for each language, we regularize the objective by introducing a soft constraint penalizing for disagreement in ar- gument labeling on aligned sentences. We propose a simple approximate learning algo- rithm for our set-up which results in efficient inference. When applied to German-English parallel data, our method obtain...