Using subcategorization knowledge to improve case prediction for translation to German
Marion Weller, Alexander Fraser and Sabine Schulte im Walde
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
This paper demonstrates the need and impact of subcategorization information for SMT. We combine (i) features on source-side syntactic subcategorization and (ii) an external knowledge base with quantitative, dependency-based information about target-side subcategorization frames. A manual evaluation for an English-to-German translation task shows that the subcategorization information has a positive impact on translation quality through better prediction of syntactic case.
Conference Manager (V2.61.0 - Rev. 2792M)