Selective Sharing for Multilingual Dependency Parsing

11 years 7 months ago

Download people.csail.mit.edu

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...

Tahira Naseem, Regina Barzilay, Amir Globerson

Real-time Traffic