Learning Head-modifier Pairs to Improve Lexicalized Dependency Parsing on a Chinese Treebank

Due to the data sparseness problem, the lexical information from a treebank for a lexicalized parser could be insufficient. This paper proposes an approach to learn head-modifier pairs from a raw corpus, and to integrate them into a lexicalized dependency parser to parse a Chinese Treebank. Experimental results show that this approach not only enlarged the coverage of bi-lexical dependency, but also improved the accuracy of dependency parsing significantly.