Broad coverage syntactic parsers such as Charniak’s parser and Collin’s parser produce as output a parse tree that only encodes local syntactic information that is a tree that does not include any empty nodes. This work presents a boosting classifier tree for modification of such parsers to add a wide variety of empty nodes and their antecedents to their parse trees. Evaluation metrics(precision, recall and F-score) were use in order to compare the performance of recovering empty nodes on parser output with the empty nodes annotations in the Penn Treebank. This evaluation of the boosting classifier tree (boosting algorithm) on the output of broad coverage syntactic parsers and Penn Treebank achieves high F-score on most types of empty nodes which leads to high parsing accuracy.