Paper: Cross-Linguistic Projection Of Role-Semantic Information

ACL ID H05-1108
Title Cross-Linguistic Projection Of Role-Semantic Information
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

This paper considers the problem of auto- matically inducing role-semantic annota- tions in the FrameNet paradigm for new languages. We introduce a general frame- work for semantic projection which ex- ploits parallel texts, is relatively inexpen- siveandcanpotentiallyreducetheamount of effort involved in creating semantic re- sources. We propose projection models that exploit lexical and syntactic informa- tion. Experimental results on an English- German parallel corpus demonstrate the advantages of this approach.