Cross-lingual model transfer using feature representation projection

Abstract

We propose a novel approach to crosslingual model transfer based on feature representation projection. First, a compact feature representation relevant for the task in question is constructed for either language independently and then the mapping between the two representations is determined using parallel data. The target instance can then be mapped into the source-side feature representation using the derived mapping and handled directly by the source-side model. This approach displays competitive performance on model transfer for semantic role labeling when compared to direct model transfer and annotation projection and suggests interesting directions for further research. © 2014 Association for Computational Linguistics.