Statistical machine translation (SMT) treats the translation of natural language as a machine learning problem. By examining many samples of human-produced translation, SMT algorithms automatically learn how to translate. SMT has made tremendous strides in less than two decades, and many popular techniques have only emerged within the last few years. This survey presents a tutorial overview of state-of-the-art SMT at the beginning of 2007. We begin with the context of the current research, and then move to a formal problem description and an overview of the four main subproblems: translational equivalence modeling, mathematical modeling, parameter estimation, and decoding. Along the way, we present a taxonomy of some different approaches within these areas. We conclude with an overview of evaluation and notes on future directions.

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

Statistical models in machine translation exhibit spurious ambiguity. That is, the probability of an output string is split among many distinct derivations (e.g., trees or segmentations). In principle, the goodness of a string is measured by the total probability of its many derivations. However, finding the best string (e.g., during decoding) is then computationally intractable. Therefore, most systems use a simple Viterbi approximation that measures the goodness of a string using only its most probable derivation. Instead, we develop a variational approximation, which considers all the derivations but still allows tractable decoding. Our particular variational distributions are parameterized as n-gram models. We also analytically show that interpolating these n-gram models for different n is similar to minimumrisk decoding for BLEU (Tromble et al., 2008). Experiments show that our approach improves the state of the art. 1

The intersection of tree transducer-based translation models with n-gram language models results in huge dynamic programs for machine translation decoding. We propose a multipass, coarse-to-fine approach in which the language model complexity is incrementally introduced. In contrast to previous orderbased bigram-to-trigram approaches, we focus on encoding-based methods, which use a clustered encoding of the target language. Across various encoding schemes, and for multiple language pairs, we show speed-ups of up to 50 times over single-pass decoding while improving BLEU score. Moreover, our entire decoding cascade for trigram language models is faster than the corresponding bigram pass alone of a bigram-to-trigram decoder. 1

Current tree-to-tree models suffer from parsing errors as they usually use only 1-best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model that uses packed forests. The model is based on a probabilistic synchronous tree substitution grammar (STSG), which can be learned from aligned forest pairs automatically. The decoder finds ways of decomposing trees in the source forest into elementary trees using the source projection of STSG while building target forest in parallel. Comparable to the state-of-the-art phrase-based system Moses, using packed forests in tree-to-tree translation results in a significant absolute improvement of 3.6 BLEU points over using 1-best trees. 1

We present a unified view of many translation algorithms that synthesizes work on deductive parsing, semiring parsing, and efficient approximate search algorithms. This gives rise to clean analyses and compact descriptions that can serve as the basis for modular implementations. We illustrate this with several examples, showing how to build search spaces for several disparate phrase-based search strategies, integrate non-local features, and devise novel models. Although the framework is drawn from parsing and applied to translation, it is applicable to many dynamic programming problems arising in natural language processing and other areas. 1

Probabilistic synchronous context-free grammar (PSCFG) translation models define weighted transduction rules that represent translation and reordering operations via nonterminal symbols. In this work, we investigate the source of the improvements in translation quality reported when using two PSCFG translation models (hierarchical and syntax-augmented), when extending a state-of-the-art phrasebased baseline that serves as the lexical support for both PSCFG models. We isolate the impact on translation quality for several important design decisions in each model. We perform this comparison on three NIST language translation tasks; Chinese-to-English, Arabic-to-English and Urdu-to-English, each representing unique challenges. 1

Edinburgh University participated in the WMT 2009 shared task using the Moses phrase-based statistical machine translation decoder, building systems for all language pairs. The system configuration was identical for all language pairs (with a few additional components for the German-English language pairs). This paper describes the configuration of the systems, plus novel contributions to Moses including truecasing, more efficient decoding methods, and a framework to specify reordering constraints. 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.

We introduce cube summing, a technique that permits dynamic programming algorithms for summing over structures (like the forward and inside algorithms) to be extended with non-local features that violate the classical structural independence assumptions. It is inspired by cube pruning (Chiang, 2007; Huang and Chiang, 2007) in its computation of non-local features dynamically using scored k-best lists, but also maintains additional residual quantities used in calculating approximate marginals. When restricted to local features, cube summing reduces to a novel semiring (k-best+residual) that generalizes many of the semirings of Goodman (1999). When non-local features are included, cube summing does not reduce to any semiring, but is compatible with generic techniques for solving dynamic programming equations. 1