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 learne...
Martins et al. (2008) presented what to the best of our knowledge still ranks as the best overall result on the CONLLX Shared Task datasets. The paper shows how triads of stacked ...
We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differenc...
Mark Dredze, John Blitzer, Partha Pratim Talukdar,...