Exploring Self-training and Co-training for Dependency Parsing

We explore the effect of self-training and co-training on Hindi dependency parsing. We use Malt parser, which is a state-ofthe-art Hindi dependency parser, and apply self-training using a large unannotated corpus. For co-training, we use MST parser with comparable accuracy to the Malt parser. Experiments are performed using two types of raw corpora— one from the same domain as the test data and another, which is out-of-domain from the test data. Through these experiments, we compare the impact of self-training and cotraining on Hindi dependency parsing.