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

We describe a scalable decoder for parsingbased machine translation. The decoder is written in JAVA and implements all the essential algorithms described in Chiang (2007): chart-parsing, m-gram language model integration, beam- and cube-pruning, and unique k-best extraction. Additionally, parallel and distributed computing techniques are exploited to make it scalable. We also propose an algorithm to maintain equivalent language model states that exploits the back-off property of m-gram language models: instead of maintaining a separate state for each distinguished sequence of “state ” words, we merge multiple states that can be made equivalent for language model probability calculations due to back-off. We demonstrate experimentally that our decoder is more than 30 times faster than a baseline decoder written in PYTHON. We propose to release our decoder as an opensource toolkit. 1

We extend discriminative n-gram language modeling techniques originally proposed for automatic speech recognition to a statistical machine translation task. In this context, we propose a novel data selection method that leads to good models using a fraction of the training data. We carry out systematic experiments on several benchmark tests for Chinese to English translation using a hierarchical phrase-based machine translation system, and show that a discriminative language model significantly improves upon a state-of-the-art baseline. The experiments also highlight the benefits of our data selection method. 1

The tree-transducer grammars that arise in current syntactic machine translation systems are large, flat, and highly lexicalized. We address the problem of parsing efficiently with such grammars in three ways. First, we present a pair of grammar transformations that admit an efficient cubic-time CKY-style parsing algorithm despite leaving most of the grammar in n-ary form. Second, we show how the number of intermediate symbols generated by this transformation can be substantially reduced through binarization choices. Finally, we describe a two-pass coarse-to-fine parsing approach that prunes the search space using predictions from a subset of the original grammar. In all, parsing time reduces by 81%. We also describe a coarse-to-fine pruning scheme for forest-based language model reranking that allows a 100-fold increase in beam size while reducing decoding time. The resulting translations improve by 1.3 BLEU. 1

Translation model size is growing at a pace that outstrips improvements in computing power, and this hinders research on many interesting models. We show how an algorithmic scaling technique can be used to easily handle very large models. Using this technique, we explore several large model variants and show an improvement 1.4 BLEU on the NIST 2006 Chinese-English task. This opens the door for work on a variety of models that are much less constrained by computational limitations.

We describe refinements to hierarchical translation search procedures intended to reduce both search errors and memory usage through modifications to hypothesis expansion in cube pruning and reductions in the size of the rule sets used in translation. Rules are put into syntactic classes based on the number of non-terminals and the pattern, and various filtering strategies are then applied to assess the impact on translation speed and quality. Results are reported on the 2008 NIST Arabic-to-English evaluation task. 1

We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, n-gram language model integration, beamand cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task. 1

A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend phrase-based decoding to allow both source and target phrasal discontinuities, which provide better generalization on unseen data and yield significant improvements to a standard phrase-based system (Moses). More interestingly, our discontinuous phrasebased system also outperforms a state-of-the-art hierarchical system (Joshua) by a very significant margin (+1.03 BLEU on average on five Chinese-English NIST test sets), even though both Joshua and our system support discontinuous phrases. Since the key difference between these two systems is that ours is not hierarchical—i.e., our system uses a string-based decoder instead of CKY, and it imposes no hard hierarchical reordering constraints during training and decoding—this paper sets out to challenge the commonly held belief that the tree-based parameterization of systems such as Hiero and Joshua is crucial to their good performance against Moses. 1