We propose a theory that gives formal semantics to word-level alignments defined over parallel corpora. We use our theory to introduce a linear algorithm that can be used to derive from word-aligned, parallel corpora the minimal set of syntactically motivated transformation rules that explain human translation data.
We offer a simple, effective, and scalable method for statistical machine translation parameter tuning based on the pairwise approach to ranking (Herbrich et al., 1999). Unlike the popular MERT algorithm (Och, 2003), our pairwise ranking optimization (PRO) method is not limited to a handful of parameters and can easily handle systems with thousands of… (More)
What do we want to learn from a translation competition and how do we learn it with confidence? We argue that a disproportionate focus on ranking competition participants has led to lots of different rankings, but little insight about which rankings we should trust. In response, we provide the first framework that allows an empirical comparison of different… (More)
Extended top-down tree transducers (transducteurs généralisés descendants [Arnold, Dauchet: Bi-transductions de forêts. ICALP'76. Edinburgh University Press. 1976]) received renewed interest in the field of Natural Language Processing. Here those transducers are extensively and systematically studied. Their main properties are identified and their relation… (More)
Darwiche has recently proposed a graphical model for driving conditioning algorithms, called a dtree, which specifies a recursive decomposition of a directed acyclic graph (DAG) into its families. A main property of a dtree is its width, and it was shown previously how to convert a DAG elimination order of width w into a dtree of width ≤ w. The importance… (More)
Conventional wisdom dictates that synchronous context-free grammars (SCFGs) must be converted to Chomsky Normal Form (CNF) to ensure cubic time decoding. For arbitrary SCFGs, this is typically accomplished via the synchronous binarization technique of (Zhang et al., 2006). A drawback to this approach is that it inflates the constant factors associated with… (More)
Recently, Halpern and Pearl proposed a definition of actual cause within the framework of structural models. In this paper , we explicate some of the assumptions underlying their definition, and re-evaluate the effectiveness of their account. We also briefly contemplate the suitability of structural models as a language for expressing subtle notions of… (More)
In this paper, we study the problem of determining actual causes of events in specific scenarios, based on a definition of actual cause proposed by Halpern and Pearl. To this end, we explore two different search-based approaches, enrich them with admissible pruning techniques and compare them experimentally. We also consider the task of designing algorithms… (More)
We present a simple preordering approach for machine translation based on a feature-rich logistic regression model to predict whether two children of the same node in the source-side parse tree should be swapped or not. Given the pair-wise children regression scores we conduct an efficient depth-first branch-and-bound search through the space of possible… (More)
Cube pruning is a fast inexact method for generating the items of a beam decoder. In this paper, we show that cube pruning is essentially equivalent to A* search on a specific search space with specific heuris-tics. We use this insight to develop faster and exact variants of cube pruning.