Abstract: Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages. We experiment with a new approach where we com-bine resources from different languages in the CoNLL 2009 shared task to build a single polyglot semantic dependency parser. Notwithstanding the absence of parallel data, and the dissimilarity in annotations between languages, our ap-proach results in improvement in parsing performance on several languages over a monolingual baseline. Analysis of the polyglot models’ performance provides a new understanding of the similarities and differences between lan-guages in the shared task.
Authors: Phoebe Mulcaire, Swabha Swayamdipta, Noah Smith (University of Washington, Carnegie Mellon University)