Ensembling Various Dependency Parsers: Adopting Turbo Parser for Indian Languages
Puneeth Kukkadapu, Deepak Kumar Malladi, Aswarth Abhilash Dara · 2012
In this paper, we describe our experiments on applying combination of Malt, MST and Turbo Parsers for Hindi dependency parsing as part of a shared task at MTPIL 2012 Workshop, COLING 2012. We explore the usage and adoption of the recently released Turbo Parser for parsing Indian languages. Various configurations of each parser are explored before combination in order to adjust them for two different settings of the data (with gold-standard and automatic Part-Of-Speech tags). We achieved a best result of 96.50 % unlabeled attachment score (UAS), 92.90 % labeled accuracy (LA), 91.49 % labeled attachment score (LAS) using voting method on data with gold POS tags. In case of data with automatic POS tags, we achieved a best result of 93.99 % UAS, 90.04 % LA and 87.84 % LAS respectively.