Probabilistic context-free grammars have the unusual property of not always defining tight distributions (i.e., the sum of the “probabilities” of the trees the grammar generates can be less than one). This paper reviews how this non-tightness can arise and discusses its impact on Bayesian estimation of PCFGs. We begin by presenting the notion of “almost everywhere tight grammars” and show that ...

Hierarchical phrase-based machine translation can capture global reordering with synchronous context-free grammar, but has little ability to evaluate the correctness of word orderings during decoding. We propose a method to integrate word-based reordering model into hierarchical phrasebased machine translation to overcome this weakness. Our approach extends the synchronous context-free grammar ...

We describe an approach to the automatic generation of convincing jazz melodies using probabilistic grammars. Uses of this approach include a software tool for assisting a soloist in the creation of a jazz solo over chord progressions. The method also shows promise as a means of automatically improvising complete solos in real-time. Our approach has been implemented and demonstrated in a free s...

Stochastic lexicalized context-free grammar (SLCFG) is an attractive compromise between the parsing e ciency of stochastic context-free grammar (SCFG) and the lexical sensitivity of stochastic lexicalized tree-adjoining grammar (SLTAG). SLCFG is a restricted form of SLTAG that can only generate contextfree languages and can be parsed in cubic time. However, SLCFG retains the lexical sensitivity...

In this paper, we describe a new algorithm for recovering WH-trace empty nodes. Our approach combines a set of hand-written patterns together with a probabilistic model. Because the patterns heavily utilize regular expressions, the pertinent tree structures are covered using a limited number of patterns. The probabilistic model is essentially a probabilistic context-free grammar (PCFG) approach...

This paper proposes a direct parsing of non-local dependencies in English. To this end, we use probabilistic linear context-free rewriting systems for data-driven parsing, following recent work on parsing German. In order to do so, we first perform a transformation of the Penn Treebank annotation of non-local dependencies into an annotation using crossing branches. The resulting treebank can be...

In this paper, we propose a paraphrasing model to address the task of system combination for machine translation. We dynamically learn hierarchical paraphrases from target hypotheses and form a synchronous context-free grammar to guide a series of transformations of target hypotheses into fused translations. The model is able to exploit phrasal and structural system-weighted consensus and also ...

We report experimental work on improving learning methods for probabilis-tic context-free grammars (PCFGs). From stacked regression we borrow the basic idea of combining grammars. Smoothing, a domain-independent method for combining grammars, does not ooer noticeable performance gains. However , PCFGs allow much tighter, domain-dependent coupling, and we show that this may be exploited for sign...

We propose several improvements to the hierarchical phrase-based MT model of Chiang (2005) and its syntax-based extension by Zollmann and Venugopal (2006). We add a source-span variance model that, for each rule utilized in a probabilistic synchronous context-free grammar (PSCFG) derivation, gives a confidence estimate in the rule based on the number of source words spanned by the rule and its ...