This paper presents a generative probabilistic dependency model of parallel texts that can be used for statistical machine translation and parallel parsing. Unlike syntactic models that are based on context-free dependency grammars, the dependency model proposed in this paper is based on a sophisticated notion of dependency grammar that is capable of modelling non-projective word order and isla...

Syntactic structures have been analysed in terms of constituent hierarchies and also in terms of dependency relations. While these two traditions have sometimes been presented as competing with each other, there is no reason in principle why syntactic dependencies and constituent hierarchies should not both be part of the grammar, complementing each other. Indeed, within transformational gramma...

Discontinuous constituents-for example, a noun and its modifying adjective separated by words unrelated to them-arc common in variable-word-order languages; Figure I shows examples. But phrase structure grammars, including ID/LP grammars, require each constituent to be a contiguous series of words. Insofar as standard parsing algorithms are based on phrase structure rules, they are inadequate f...

We present a new family of models for unsupervised parsing, Dependency and Boundary models, that use cues at constituent boundaries to inform head-outward dependency tree generation. We build on three intuitions that are explicit in phrase-structure grammars but only implicit in standard dependency formulations: (i) Distributions of words that occur at sentence boundaries — such as English dete...

Results of computational complexity exist for a wide range of phrase structure-based grammar formalisms, while there is an apparent lack of such results for dependency-based formalisms. We here adapt a result on the complexity of ID/LP-grammars to the dependency framework. Contrary to previous studies on heavily restricted dependency grammars, we prove that recognition (and thus, parsing) of li...

This paper presents a reesthnation algorithm and a best-first parsing (BFP) algorithm for probabilistic dependency grummars (PDG). The proposed reestimation algorithm is a variation of the inside-outside algorithm adapted to probabilistic dependency grammars. The inside-outside algorithm is a probabilistic parameter reestimation algorithm for phrase structure grammars in Chomsky Normal Form (CN...

We present a family of priors over probabilistic grammar weights, called the shared logistic normal distribution. This family extends the partitioned logistic normal distribution, enabling factored covariance between the probabilities of different derivation events in the probabilistic grammar, providing a new way to encode prior knowledge about an unknown grammar. We describe a variational EM ...

We propose a formal characterization of variation in the syntactic realization of semantic arguments, using hierarchies of syntactic relations and thematic roles, and a mechanism of lexical inheritance to obtain valency frames from individual linking types. We embed the formalization in the new lexicalized, dependency-based grammar formalism of Topological Dependency Grammar (TDG) (Duchier and ...

This paper presents a rule-based formalism for dependency annotation within the Constraint Grammar framework, implemented as an extension of the open source CG3 compiler. As a proof of concept we have constructed a complete dependency grammar for Esperanto, building on morphosyntactically annotated input from the EspGram parser. The system is described and evaluated on a test corpus. With a 4% ...

In the past, a divide could be seen between ’deep’ parsers on the one hand, which construct a semantic representation out of their input, but usually have significant coverage problems, and more robust parsers on the other hand, which are usually based on a (statistical) model derived from a treebank and have larger coverage, but leave the problem of semantic interpretation to the user. More re...