The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2017, one of two tasks was devoted to learning dependency parsers for a large number of languages, in a realworld setting without any gold-standard annotation on input. All test sets followed a unified annotation scheme, namely that of Universal Dependencies. In this paper, we define the task and evaluation methodology, describe data preparation, report and analyze the main results, and provide a brief categorization of the different approaches of the participating systems.

Universal dependencies (UD) is a framework for morphosyntactic annotation of human language, which to date has been used to create treebanks for more than 100 languages. In this article, we outline the linguistic theory of the UD framework, which draws on a long tradition of typologically oriented grammatical theories. Grammatical relations between words are centrally used to explain how predicate–argument structures are encoded morphosyntactically in different languages while morphological features and part-of-speech classes give the properties of words. We argue that this theory is a good basis for cross-linguistically consistent annotation of typologically diverse languages in a way that supports computational natural language understanding as well as broader linguistic studies.

The present paper outlines an ongoing project of annotation of the extended nominal coreference and the bridging anaphora in the Prague Dependency Treebank. We describe the annotation scheme with respect to the linguistic classification of coreferential and bridging relations and focus also on details of the annotation process from the technical point of view. We present methods of helping the annotators -by a pre-annotation and by several useful features implemented in the annotation tool. Our method of the inter-annotator agreement is focused on the improvement of the annotation guidelines; we present results of three subsequent measurements of the agreement.

The paper describes the system for coreference resolution in German and Russian, trained exclusively on coreference relations projected through a parallel corpus from English. The resolver operates on the level of deep syntax and makes use of multiple specialized models. It achieves 32 and 22 points in terms of CoNLL score for Russian and German, respectively. Analysis of the evaluation results show that the resolver for Russian is able to preserve 66% of the English resolver's quality in terms of CoNLL score. The system was submitted to the Closed track of the COR-BON 2017 Shared task.

No abstract