Investigating Multilingual Dependency Parsing

In this paper, we describe a system for the CoNLL-X shared task of multilingual dependency parsing. It uses a baseline Nivre’s parser (Nivre, 2003) that first identifies the parse actions and then labels the dependency arcs. These two steps are implemented as SVM classifiers using LIBSVM. Features take into account the static context as well as relations dynamically built during parsing. We experimented two main additions to our implementation of Nivre’s parser: N best search and bidirectional parsing. We trained the parser in both left-right and right-left directions and we combined the results. To construct a single-head, rooted, and cycle-free tree, we applied the ChuLiu/Edmonds optimization algorithm. We ran the same algorithm with the same parameters on all the languages.