Multilingual Dependency Analysis with a Two-Stage Discriminative Parser

Proceedings of the 10th Conference on Computational Natural Language Learning (CoNLL-X), pages 216–220, New York City, June 2006. c⃝2006 Association for Computational Linguistics Multilingual Dependency Analysis with a Two-Stage Discriminative Parser Ryan McDonald Kevin Lerman Fernando Pereira Department of Computer and Information Science University of Pennsylvania Philadelphia, PA {ryantm,klerman,pereira}@cis.upenn.edu Abstract We present a two-stage multilingual de- pendency parser and evaluate it on 13 diverse languages. The first stage is based on the unlabeled dependency pars- ing models described by McDonald and Pereira (2006) augmented with morpho- logical features for a subset of the lan- guages. The second stage takes the out- put from the first and labels all the edges in the dependency graph with appropri- ate syntactic categories using a globally trained sequence classifier over compo- nents of the graph. We report results on the CoNLL-X shared task (Buchholz et al., 2006) data sets and present an error analysis. 1 Introduction Often in language processing we require a deep syn- tactic representation of a sentence in order to assist further processing. With the availability of resources such as the Penn WSJ Treebank, much of the fo- cus in the parsing community had been on producing syntactic representations based on phrase-structure. However, recently their has been a revived interest in parsing models that produce dependency graph representations of sentences, which model words and their arguments through directed edges (Hud- son, 1984; Mel′ˇcuk, 1988). This interest has gener- ally come about due to the computationally efficient and flexible nature of dependency graphs and their ability to easily model non-projectivity in freer-word order languages. Nivre (2005) gives an introduction to dependency representations of sentences and re- cent developments in dependency parsing strategies. Dependency graphs also encode much of the deep syntactic information needed for further process- ing. This has been shown through their success- ful use in many standard natural language process- ing tasks, including machine translation (Ding and Palmer, 2005), sentence compression (McDonald, 2006), and textual inference (Haghighi et al., 2005). In this paper we describe a two-stage discrimi- native parsing approach consisting of an unlabeled parser and a subsequent edge labeler. We evaluate this parser on a diverse set of 13 languages using data provided by the CoNLL-X shared-task organiz- ers (Buchholz et al., 2006; Hajiˇc et al., 2004; Simov et al., 2005; Simov and Osenova, 2003; Chen et al., 2003; B¨ohmov´a et al., 2003; Kromann, 2003; van der Beek et al., 2002; Brants et al., 2002; Kawata and Bartels, 2000; Afonso et al., 2002; Dˇzeroski et al., 2006; Civit Torruella and Mart´ı Anton´ın, 2002; Nilsson et al., 2005; Oflazer et al., 2003; Atalay et al., 2003). The results are promising and show the language independence of our system under the as- sumption of a labeled dependency corpus in the tar- get language. For the remainder of this paper, we denote by x = x1, . . . xn a sentence with n words and by y a corresponding dependency graph. A depen- dency graph is represented by a set …

Content truncated to 500 words