We compare three different approaches to parsing into syntactic, bi-lexical dependencies for English: a ‘direct’ data-driven dependency parser, a statistical phrase structure parser, and a hybrid, ‘deep’ grammar-driven parser. The analyses from the latter two are post-converted to bilexical dependencies. Through this ‘reduction’ of all three approaches to syntactic dependency parsers, we determ...

We present gdbank, a small handbuilt corpus of 32 sentences with dependency structures and categorial grammar type assignments. The sentences have been chosen to illustrate as broad a range of the unusual features of Scottish Gaelic as possible, particularly nouns being used to represent psychological states where more thoroughly-studied languages such as English and French would prefer a verb,...

Statistical parsers need huge annotated treebanks to learn from and building treebanks is an expensive proposition. To create parsers for different grammar formalisms in a language, building separate treebanks for each of those isn’t a feasible task. Treebanks available in one formalism can be converted into an other either automatically or with minimal human effort by exploiting the similariti...

This paper addresses a hot topic of Hungarian syntactic research, viz. the treatment of “discontinuous” constructions involving auxiliaries. The case is made for a projective dependency grammar (DG) account built on the notions of rising and catenae (Groß and Osborne, 2009). Additionally, the semantic basis of the dependency created by rising is described with a view to analogy and construction...

Pure statistical parsing systems achieves high in-domain accuracy but performs poorly out-domain. In this paper, we propose two different approaches to produce syntactic dependency structures using a large-scale hand-crafted HPSG grammar. The dependency backbone of an HPSG analysis is used to provide general linguistic insights which, when combined with state-of-the-art statistical dependency p...

We present an approach to text simplification based on synchronous dependency grammars. The higher level of abstraction afforded by dependency representations allows for a linguistically sound treatment of complex constructs requiring reordering and morphological change, such as conversion of passive voice to active. We present a synchronous grammar formalism in which it is easy to write rules ...

Syntax-based statistical machine translation (MT) aims at applying statistical models to structured data. In this paper, we present a syntax-based statistical machine translation system based on a probabilistic synchronous dependency insertion grammar. Synchronous dependency insertion grammars are a version of synchronous grammars defined on dependency trees. We first introduce our approach to ...

A prominent tradition within the framework of Head-Driven Phrase Structure Grammar (HPSG, Pollard and Sag 1994) has argued on linguistic grounds for analyses which license so-called discontinuous constituents (Reape 1993; Kathol 1995; Richter and Sailer 2001; Müller 1999a; Penn 1999; Donohue and Sag 1999; Bonami et al. 1999), joining researchers in other linguistic frameworks, including Depende...

This paper discusses the adaptation of the Stanford typed dependency model (de Marneffe and Manning 2008), initially designed for English, to the requirements of typologically different languages from the viewpoint of practical parsing. We argue for a framework of functional dependency grammar that is based on the idea of parallelism between syntax and semantics. There is a twofold challenge: (...

Broad-coverage annotated treebanks necessary to train parsers do not exist for many resource-poor languages. The wide availability of parallel text and accurate parsers in English has opened up the possibility of grammar induction through partial transfer across bitext. We consider generative and discriminative models for dependency grammar induction that use word-level alignments and a source ...