Selective sharing for multilingual dependency parsing

• Authors: Tahira Naseem;Regina Barzilay;Amir Globerson
• Venue: ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
• Year: 2012

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 language-universal, 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 multi-lingual parser. The largest improvement is achieved on the non Indo-European languages yielding a gain of 14.4%.