Selective Sharing for Multilingual Dependency Parsing

We present a novel algorithm for multilingual dependency parsing that uses annotations from a diverse set of source languages to parse a new unannotated language. Our motivation is to broaden the advantages of multilingual learning to languages that exhibit significant differences from existing resource-rich languages. The algorithm learns which aspects of the source languages are relevant for the target language and ties model parameters accordingly. The model factorizes the process of generating a dependency tree into two steps: selection of syntactic dependents and their ordering. Being largely languageuniversal, the selection component is learned in a supervised fashion from all the training languages. In contrast, the ordering decisions are only influenced by languages with similar properties. We systematically model this cross-lingual sharing using typological features. In our experiments, the model consistently outperforms a state-of-the-art multilingual parser. The largest im...

• Type: Journal
• Year: 2012
• Where: ACL
• Authors: Tahira Naseem, Regina Barzilay, Amir Globerson
• Keywords: ACL 2012, Computational Linguistics, Indo European Languages, Rich Languages, Target Language