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 National Competence Centres (NCCs) in ELG are an international network of 32 regional and national networks, lead by one regional/national representative. The 32 NCCs play a crucial role in ELG, they support the project by bringing in their corresponding regional and national perspective and stakeholders, organising ELG workshops and functioning as regional/national representatives. The chapter explains why, despite a considerable coordination effort, it was worth putting this network together. One important task carried out by the NCCs was to conduct regional/ national dissemination events and to participate in relevant regional/national events and also in the annual META-FORUM conferences, organised by ELG.

The European Language Grid is meant to develop into the primary platform of the European Language Technology community. In addition to LT tools and services (Chapter 7) and Language Resources (Chapter 8), ELG represents the actual members of this community, i. e., the companies and research organisations that develop language technologies and that are engaged in related activities. The goal of becoming the primary platform for LT in Europe implies that ELG should ideally represent all European companies and all European research organisations with corresponding metadata records in the ELG catalogue, which are interlinked with the respective LT tools and services as well as language resources they offer. This chapter describes the European stakeholders and user groups that are relevant for the ELG initiative, the composition of the community and the locations of the companies and research groups as currently listed in ELG. Furthermore, we describe a number of technical and organisational challenges involved in the preparation of our list of stakeholders, and outline the process of catalogue population.