Tree revision learning for dependency parsing

We present a revision learning model for improving the accuracy of a dependency parser. The revision stage corrects the output of the base parser by means of revision rules learned from the mistakes of the base parser itself. Revision learning is performed with a discriminative classifier. The revision stage has linear complexity and preserves the efficiency of the base parser. We present empirical evaluations on the treebanks of two languages, which show effectiveness in relative error reduction and state of the art accuracy.