In order to realize the full potential of dependency-based syntactic parsing, it is desirable to allow non-projective dependency structures. We show how a datadriven deterministic dependency parser, in itself restricted to projective structures, can be combined with graph transformation techniques to produce non-projective structures. Experiments using data from the Prague Dependency Treebank show that the combined system can handle nonprojective constructions with a precision sufficient to yield a significant improvement in overall parsing accuracy. This leads to the best reported performance for robust non-projective parsing of Czech. 1

Despite a long and venerable tradition in descriptive linguistics, dependency grammar has until recently played a fairly marginal role both in theoretical linguistics and in natural language processing. The increasing interest in dependency-based

Because of the wide variety of contemporary practices used in the automatic syntactic parsing of natural languages, it has become necessary to analyze and evaluate the strengths and weaknesses of different approaches. This research is all the more necessary because there are currently no genre- and domain-independent parsers that are able to analyze unrestricted text with 100% preciseness (I use this term to refer to the correctness of analyses assigned by a parser). All these factors create a need for methods and resources that can be used to evaluate and compare parsing systems. This research describes: (1) A theoretical analysis of current achievements in parsing and parser evaluation. (2) A framework (called FEPa) that can be used to carry out practical parser evaluations and comparisons. (3) A set of new evaluation resources: FiEval is a Finnish treebank under construction, and MGTS and RobSet are parser evaluation resources in English. (4) The results of experiments in which the developed evaluation framework and the two resources for English were used for evaluating a set of selected parsers.

Abstract. Typological diversity among the natural languages of the world poses interesting challenges for the models and algorithms used in syntactic parsing. In this paper, we apply a data-driven dependency parser to Turkish, a language characterized by rich morphology and flexible constituent order, and study the effect of employing varying amounts of morpholexical information on parsing performance. The investigations show that accuracy can be improved by using representations based on inflectional groups rather than word forms, confirming earlier studies. In addition, lexicalization and the use of rich morphological features are found to have a positive effect. By combining all these techniques, we obtain the highest reported accuracy for parsing the Turkish Treebank. 1

We introduce a systematic approach to language change quantification by studying unconsciously used language features in time-separated parallel translations. For this purpose, we use objective style markers such as vocabulary richness and lengths of words, word stems and suffixes, and employ statistical methods to measure their changes over time. In this study, we focus on the change in Turkish in the second half of the twentieth century. To obtain word stems, we first introduce various stemming techniques and show that they are highly effective. Our statistical analyses show that over time, for both text and lexicon, the length of Turkish words has become significantly longer, and word stems have become significantly shorter. We also show that suffix lengths have become significantly longer for types and the vocabulary richness based on word stems has shrunk significantly. These observations indicate that in contemporary Turkish one would use more suffixes to compensate for the fewer stems to preserve the expressive power of the language at the same level. Our approach can be adapted for quantifying the change in other languages.