Previous work on dependency parsing used various kinds of combination models but a systematic analysis and comparison of these approaches is lacking. In this paper we implemented such a study for English dependency parsing and find several non-obvious facts: (a) the diversity of base parsers is more important than complex models for learning (e.g., stacking, supervised meta-classification), (b) approximate, linear-time re-parsing algorithms guarantee well-formed dependency trees without significant performance loss, and (c) the simplest scoring model for re-parsing (unweighted voting) performs essentially as well as other more complex models. This study proves that fast and accurate ensemble parsers can be built with minimal effort. 1

The Evalita ’07 Parsing Task has been the first contest among parsing systems for Italian. It is the first attempt to compare the approaches and the results of the existing parsing systems specific for this language using a common treebank annotated using both a dependency and a constituency-based format. The development data set for this parsing competition was taken from the Turin University Treebank, which is annotated both in dependency and constituency format. The evaluation metrics were those standardly applied in CoNLL and PARSEVAL. The results of the parsing results are very promising and higher than the state-of-the-art for dependency parsing of Italian. An analysis of such results is provided, which takes into account other experiences in treebank-driven parsing for Italian and for other Romance languages (in particular, the CoNLL X & 2007 shared tasks for dependency parsing). It focuses on the characteristics of data sets, i.e. type of annotation and size, parsing paradigms and approaches applied also to languages other than Italian. 1.

Abstract. This paper describes our participation in the EVALITA 2009 Dependency Parsing Task with a version of MaltParser. Reusing feature models developed in the CoNLL shared task 2007, we evaluated four different parsing algorithms implemented in MaltParser and found that the best results were achieved with Covington’s non-projective parsing algorithm. In the final evaluation, our system finished third in the main task and second in the pilot task. Keywords: Dependency parsing, Italian. 1

We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shiftreduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72 % and 91.65 % respectively, which compare well with similar previous models and the state-of-the-art. 1

Abstract not found

Since chunking can be performed efficiently and accurately, it is attractive to use it as a preprocessing step in full parsing stages. We analyze whether providing chunk data to a statistical dependency parser can benefit its accuracy. We present a set of experiments meant to select first a set of features that provide the greates improvement to a Shift/Reduce dependency parser, then to determine an appropriate feature model. We report on accuracy gain obtained using features from chunks produced using a statistical chunker as well as from an approximate representation of noun phrases induced directly by the parser. Finally we analyze the degree of accuracy that such a parser can achieve in chunking compared to a specialized statistical chunker. 1.

Deterministic transition-based Shift/Reduce dependency parsers make often mistakes in the analysis of long span dependencies (McDonald & Nivre, 2007). Titov and Henderson (2007) address this accuracy

stage constraint based hybrid approach to free word order language

The tremendous improvement in robustness and accuracy of natural language parsing that we have witnessed during the last decade has almost exclusively been concerned with the analysis of written texts. The development of equally accurate syntactic parsers for spoken language is one of the greatest challenges for the parsing community. In this paper, we report the first results on parsing spoken Swedish with a data-driven dependency parser previously evaluated on written texts from a wide variety of languages. We compare two different algorithms, one restricted to projective dependency structures and one that allows non-projective structures, and compare the results to those obtained for written Swedish using the same methodology. The results show that parsing accuracy is still lower for spoken language than for written language, although part of the difference can be explained by properties of the transcribed spoken corpus used in the experiments. The results also show that the capacity to derive non-projective dependency structures is more crucial for spoken Swedish than for written Swedish.

We combine multiple word representations based on semantic clusters extracted from the (Brown et al., 1992) algorithm and syntactic clusters obtained from the Berkeley parser (Petrov et al., 2006) in order to improve discriminative dependency parsing in the MST-Parser framework (McDonald et al., 2005). We also provide an ensemble method for combining diverse cluster-based models. The two contributions together significantly improves unlabeled dependency accuracy from 90.82% to 92.13%. 1