We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free grammars. Using a single unified internal representation for translation forests, the decoder strictly separates model-specific translation logic from general rescoring, pruning, and inference algorithms. From this unified representation, the decoder can extract not only the 1- or k-best translations, but also alignments to a reference, or the quantities necessary to drive discriminative training using gradient-based or gradient-free optimization techniques. Its efficient C++ implementation means that memory use and runtime performance are significantly better than comparable decoders. 1

Despite many differences between phrase-based, hierarchical, and syntax-based translation models, their training and testing pipelines are strikingly similar. Drawing on this fact, we extend the Moses toolkit to implement hierarchical and syntactic models, making it the first open source toolkit with end-to-end support for all three of these popular models in a single package. This extension substantially lowers the barrier to entry for machine translation research across multiple models. 1.

Translation systems are complex, and most metrics do little to pinpoint causes of error or isolate system differences. We use a simple technique to discover induction errors, which occur when good translations are absent from model search spaces. Our results show that a common pruning heuristic drastically increases induction error, and also strongly suggest that the search spaces of phrase-based and hierarchical phrase-based models are highly overlapping despite the well known structural differences. 1

We present a machine translation framework that can incorporate arbitrary features of both input and output sentences. The core of the approach is a novel decoder based on lattice parsing with quasisynchronous grammar (Smith and Eisner, 2006), a syntactic formalism that does not require source and target trees to be isomorphic. Using generic approximate dynamic programming techniques, this decoder can handle “non-local ” features. Similar approximate inference techniques support efficient parameter estimation with hidden variables. We use the decoder to conduct controlled experiments on a German-to-English translation task, to compare lexical phrase, syntax, and combined models, and to measure effects of various restrictions on nonisomorphism. 1

Many statistical translation models can be regarded as weighted logical deduction. Under this paradigm, we use weights from the expectation semiring (Eisner, 2002), to compute first-order statistics (e.g., the expected hypothesis length or feature counts) over packed forests of translations (lattices or hypergraphs). We then introduce a novel second-order expectation semiring, which computes second-order statistics (e.g., the variance of the hypothesis length or the gradient of entropy). This second-order semiring is essential for many interesting training paradigms such as minimum risk, deterministic annealing, active learning, and semi-supervised learning, where gradient descent optimization requires computing the gradient of entropy or risk. We use these semirings in an open-source machine translation toolkit, Joshua, enabling minimum-risk training for a benefit of up to 1.0 BLEU point.

Abstract. Nowadays information systems are required to be more adaptable and flexible than before to deal with the rapidly increasing quantity of available data and changing information needs. Text Classification (TC) is a useful task that can help to solve different problems in different fields. This paper investigates the application of descriptive approaches for modelling classification. The main objectives are increasing abstraction and flexibility so that expert users are able to customise specific strategies for their needs. The contribution of this paper is two-fold. Firstly, it illustrates that the modelling of classifiers in a descriptive approach is possible and it leads to a close definition w.r.t. mathematical formulations. Moreover, the automatic translation from PDatalog to mathematical formulation is discussed. Secondly, quality and efficiency results prove the approach feasibility for real-scale collections. 1