Each year the Conference on Computational Natural Language Learning (CoNLL) 1 features a shared task, in which participants train and test their systems on exactly the same data sets, in order to better compare systems. The tenth CoNLL (CoNLL-X) saw a shared task on Multilingual Dependency Parsing. In this paper, we describe how treebanks for 13 languages were converted into the same dependency format and how parsing performance was measured. We also give an overview of the parsing approaches that participants took and the results that they achieved. Finally, we try to draw general conclusions about multi-lingual parsing: What makes a particular language, treebank or annotation scheme easier or harder to parse and which phenomena are challenging for any dependency parser? Acknowledgement Many thanks to Amit Dubey and Yuval Krymolowski, the other two organizers of the shared task, for discussions, converting treebanks, writing software and helping with the papers. 2

Abstract not found

Deterministic parsing guided by treebankinduced classifiers has emerged as a simple and efficient alternative to more complex models for data-driven parsing. We present a systematic comparison of memory-based learning (MBL) and support vector machines (SVM) for inducing classifiers for deterministic dependency parsing, using data from Chinese, English and Swedish, together with a variety of different feature models. The comparison shows that SVM gives higher accuracy for richly articulated feature models across all languages, albeit with considerably longer training times. The results also confirm that classifier-based deterministic parsing can achieve parsing accuracy very close to the best results reported for more complex parsing models. 1

In this thesis we develop a discriminative learning method for dependency parsing using online large-margin training combined with spanning tree inference algorithms. We will show that this method provides state-of-the-art accuracy, is extensible through the feature set and can be implemented efficiently. Furthermore, we display the language independent nature of the method by evaluating it on over a dozen diverse languages as well as show its practical applicability through integration into a sentence compression system. We start by presenting an online large-margin learning framework that is a generaliza- tion of the work of Crammer and Singer [34, 37] to structured outputs, such as sequences and parse trees. This will lead to the heart of this thesis – discriminative dependency pars- ing. Here we will formulate dependency parsing in a spanning tree framework, yielding efficient parsing algorithms for both projective and non-projective tree structures. We will then extend the parsing algorithm to incorporate features over larger substructures with- out an increase in computational complexity for the projective case. Unfortunately, the non-projective problem then becomes NP-hard so we provide structurally motivated ap- proximate algorithms. Having defined a set of parsing algorithms, we will also define a rich feature set and train various parsers using the online large-margin learning framework. We then compare our trained dependency parsers to other state-of-the-art parsers on 14 diverse languages: Arabic, Bulgarian, Chinese, Czech, Danish, Dutch, English, German, Japanese, Portuguese, Slovene, Spanish, Swedish and Turkish. Having built an efficient and accurate discriminative dependency parser, this thesis will then turn to improving and applying the parser. First we will show how additional re- sources can provide useful features to increase parsing accuracy and to adapt parsers to new domains. We will also argue that the robustness of discriminative inference-based learning algorithms lend themselves well to dependency parsing when feature representa- tions or structural constraints do not allow for tractable parsing algorithms. Finally, we integrate our parsing models into a state-of-the-art sentence compression system to show its applicability to a real world problem.

typology forms a basis for the error type code attached to each entry in the Error Corpora Database (ECD), and for the parser in the resulting proof-reading system. It is of great importance in the development of the proof-reading tool to know what types of errors that in fact occur in newspapers, and to have these systematised in an appropriate manner. Potential errors have not been considered, which means that the typology is solely based on factual errors and not on hypothetical ones. The Swedish newspapers Svenska Dagbladet and Upsala Nya Tidning have supplied material for the development of the error typology and the ECD where all the error instances with their corrections and error types codes are stored. The language errors have been detected and corrected by professional proofreaders at the newspapers. The typology is descriptive, not normative. There are at least four possible dimensions according to which a division between errors could be made: the nature of the error, the c

Abstract not found

With reference to particular problems of interpretations that radio listeners of today are likely to encounter when listening to a Norwegian radio reportage from the 1930s, this article discusses the question of whether it is possible for present-day readers/viewers/ listeners or text analysts to understand texts from the past in the way that they were originally meant to be understood. It is argued that we need to gain some kind of access to the contexts that once engendered the texts if we are to arrive at historically acceptable interpretations and explanations of them. The article suggests a solution to the problem of historical text analysis, namely historical context reconstruction. This solution is concretised in terms of a specific methodology, which has here been used for research on the formation and first development of the genre system of Norwegian radio. This methodology involves the application of three different text-context models for discourse-analytical purposes: 1. Halliday’s structural correlation model 2. The multistratal realisation model developed within social semiotics 3. Goffman’s frame model. Key Words: historical text analysis, historical context reconstruction, discourse-analytical methodologies, radio reportage, Norway

my friend, my love and my guiding-star Acknowledgements First and foremost, I wish to express my gratitude to my supervisor, Christer Platzack, who has endured the task of supervising someone who has a wider range of interests than is presumably desirable; I would never have wished to supervise myself. Thank you, Christer, for reading and discussing different versions of my thesis with enthusiasm in order to improve it and for your subtle intuition regarding when to criticise and when to encourage. Furthermore, I thank you for always taking time to discuss both Small Clause problems and life problems, depending on what has been most urgent at the time. Next, I wish to thank Gunlög Josefsson for her invaluable comments on an earlier version of this thesis – your insightful suggestions and important remarks have helped me a great deal.

Tesnière (1959) is often regarded as the founder of the modern theoretical tradition of dependency grammar, but it is not one well-defined theory. Instead, it comprises several related theories, having some core notions in common. Such a notion is the directed relations between pairs of lexical elements, but the formalism and the criteria for

Development of a grammar and a graphical