Paper: Cross-Lingual Induction for Deep Broad-Coverage Syntax: A Case Study on German Participles

ACL ID C10-2163
Title Cross-Lingual Induction for Deep Broad-Coverage Syntax: A Case Study on German Participles
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

This paper is a case study on cross-lingual induction of lexical resources for deep, broad-coverage syntactic analysis of Ger- man. We use a parallel corpus to in- duce a classifier for German participles which can predict their syntactic category. By means of this classifier, we induce a resource of adverbial participles from a huge monolingual corpus of German. We integrate the resource into a German LFG grammar and show that it improves pars- ing coverage while maintaining accuracy.