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

The duality of objects and relationships is so deeply embedded in our thinking that almost all modelling languages include it as a fundamental distinction. Yet there is evidence that the two are naturally complemented by a third, equally fundamental notion: that of roles. Although definitions of the role concept abound in the literature, we maintain that only few are truly original, and that even fewer acknowledge the intrinsic role of roles as intermediaries between relationships and the objects that engage in them. After discussing the major families of role conceptualizations, we present our own basic definition and demonstrate how it naturally accounts for many modelling issues, including multiple and dynamic classification, object collaboration, polymorphism, and substitutability. <3 2000 Elsevier Science B.V. All rights reserved.

Abstract not found

We describe in this paper the ML system, ASIUM, which learns subcategorization frames of verbs and ontologies from syntactic parsing of technical texts in natural language. The restrictions of selection in the subcategorization frames are filled by the concepts of the ontology. Applications requiring subcategorization frames and ontologies are crucial and numerous. The most direct applications are semantic checking of texts and syntactic parsing improvement but also text generation and translation. The inputs of ASIUM result from syntactic parsing of texts, they are subcategorization examples and basic clusters formed by head words that occur with the same verb after the same preposition (or with the same syntactical role). ASIUM successively aggregates the clusters to form new concepts in the form of a generality graph that represents the ontology of the domain. Subcategorization frames are learned in parallel, so that as concepts are formed, they fill restrictions of selection in th...

Traditionally, vector-based semantic space models use word co-occurrence counts from large corpora to represent lexical meaning. In this article we present a novel framework for constructing semantic spaces that take syntactic relations into account. We introduce a formalization for this class of models which allows linguistic knowledge to guide the construction process. We evaluate our framework on a range of tasks relevant for cognitive science and natural language processing: semantic priming, synonymy detection and word sense disambiguation. In all cases, our framework obtains results that are comparable or superior to the state of the art. 1.

Abstract. In this paper, we present a unified feature-based theory of complement, adjunct, and subject extraction, in which there is no need either for valence reducing lexical rules or for phonologically null traces. Our analysis rests on the assumption that the mapping between argument structure and valence is defined by realization constraints which are satisfied by all lexical heads. Arguments can be realized as local dependents, in which case they are selected via the head’s valence features. Alternatively, arguments may be realized in a long-distance dependency construction, in which case they are selected via the head’s SLASH features. Furthermore, we argue that in English post-verbal adjuncts, as well as complements, are syntactic dependents selected by the verb, thus providing a uniform analysis of complement and adjunct extraction. Finally, we provide an alternative treatment of subject extraction which is subsumed by our general analysis and offer a new account of the that-trace effect. 1.

We describe in this paper the ML system, Asium, which learns subcategorization frames of verbs and ontologies from syntactic parsing of technical texts in natural language. The restrictions of selection in the subcategorization frames are filled by the concepts of the ontology. Applications requiring subcategorization frames and ontologies are crucial and numerous. The most direct applications are semantic checking of texts and syntactic parsing improvement but also text generation and translation. The input of Asium result from syntactic parsing of texts, they are subcategorization examples and basic clusters formed by head words that occur with the same verb after the same preposition (or with the same syntactical role). Asium successively aggregates the clusters to form new concepts in the form of a generality graph that represents the ontology of the domain. Subcategorization frames are learned in parallel, so that as concepts are formed, they fill restrictions of selection in the ...

Parsing algorithms that process the input from left to right and construct a single derivation have often been considered inadequate for natural language parsing because of the massive ambiguity typically found in natural language grammars. Nevertheless, it has been shown that such algorithms, combined with treebank-induced classifiers, can be used to build highly accurate disambiguating parsers, in particular for dependency-based syntactic representations. In this article, we first present a general framework for describing and analyzing algorithms for deterministic incremental dependency parsing, formalized as transition systems. We then describe and analyze two families of such algorithms: stack-based and list-based algorithms. In the former family, which is restricted to projective dependency structures, we describe an arc-eager and an arc-standard variant; in the latter family, we present a projective and a nonprojective variant. For each of the four algorithms, we give proofs of correctness and complexity. In addition, we perform an experimental evaluation of all algorithms in combination with SVM classifiers for predicting the next parsing action, using data from thirteen languages. We show that all four algorithms give competitive accuracy, although the non-projective list-based algorithm generally outperforms the projective algorithms for languages with a non-negligible proportion of non-projective constructions. However, the projective algorithms often produce comparable results when combined with the technique known as pseudo-projective parsing. The linear time complexity of the stack-based algorithms gives them an advantage with respect to efficiency both in learning and in parsing, but the projective list-based algorithm turns out to be equally efficient in practice. Moreover, when the projective algorithms are used to implement pseudo-projective parsing, they sometimes become less efficient in parsing (but not in learning) than the non-projective list-based algorithm. Although most of the algorithms have been partially described in the literature before, this is the first comprehensive analysis and evaluation of the algorithms within a unified framework. 1.

Abstract not found

In this paper we investigate several nonprojective parsing algorithms for dependency parsing, providing novel polynomial time solutions under the assumption that each dependency decision is independent of all the others, called here the edge-factored model. We also investigate algorithms for non-projective parsing that account for nonlocal information, and present several hardness results. This suggests that it is unlikely that exact non-projective dependency parsing is tractable for any model richer than the edge-factored model. 1