Transferring Semantic Roles Using Translation and Syntactic Information
This addresses the challenge of limited annotated data for semantic role labeling in low-resource languages, though it is incremental.
The paper tackles the problem of semantic role labeling for resource-poor languages by transferring annotations from a resource-rich language using parallel data, resulting in a 3.5 absolute labeled F-score improvement over a standard method.
Our paper addresses the problem of annotation projection for semantic role labeling for resource-poor languages using supervised annotations from a resource-rich language through parallel data. We propose a transfer method that employs information from source and target syntactic dependencies as well as word alignment density to improve the quality of an iterative bootstrapping method. Our experiments yield a $3.5$ absolute labeled F-score improvement over a standard annotation projection method.