Neural network (“deep learning”) models are taking over machine learning approaches for language by storm. In particular, recurrent neural networks (RNNs), which are flexible non-markovian models of sequential data, were shown to be effective for a variety of language processing tasks. Somewhat surprisingly, these seemingly purely sequential models are very capable at modeling syntactic phenome...

In this paper, we present a revision of the training set of the METU-Sabancı Turkish syntactic dependency treebank composed of 4997 sentences in accordance with the principles of the Meaning-Text Theory (MTT). MTT reflects the multilayered nature of language by a linguistic model in which each linguistic phenomenon is treated at its corresponding level(s). Our analysis of the METU-Sabancı synta...

We present SETIMES.HR— the first linguistically annotated corpus of Croatian that is freely available for all purposes. The corpus is built on top of the SETIMES parallel corpus of nine Southeast European languages and English. It is manually annotated for lemmas, morphosyntactic tags, named entities and dependency syntax. We couple the corpus with domain-sensitive test sets for Croatian and Se...

An adequate, complete, and economical linguistic theory is necessary for MT and the question is whether a consistent use of the often unduly neglected dependency syntax, including a systematic description of topic and focus, cannot serve as a reliable base for the grammar of an interlingua, or of a set of interrelated interface structures. i. As Slocum (198~)convinc~ly shows, the attitude towar...

We describe results of investigation of a specific type of discontinuous constructions, namely non-projective constructions concerning verbs and their arguments. This topic is especially important for languages with a relatively free word order, such as Czech, which is the language we have primarily worked with. For comparison, we have included some results for English. The corpora used for bot...

We are interested in a graph-based Knowledge Representation formalism that would allow for the representation, manipulation, query, and reasoning over dependency structures, and linguistic knowledge of the Explanatory and Combinatorial Dictionary in the Meaning-Text Theory framework. Neither the semantic web formalisms nor the conceptual graphs appear to be suitable for this task, and this led ...

This paper shows how the correspondence between a unordered dependency tree and a sentence that expresses it can be achieved by transforming the tree into a string where each linear precedence link corresponds to one specific syntactic relation. We propose a formal grammar with a distributed architecture that can be used for both synthesis and analysis. We argue for the introduction of a topolo...