This paper is a survey of the current machine translation research in the US, Europe and Japan. A short history of machine translation is presented first, followed by an overview of the current research work. Representative examples of a wide range of different approaches adopted by machine translation researchers are presented. These are described in detail along with a discussion of the practicalities of scaling up these approaches for operational environments. In support of this discussion, issues in, and techniques for, evaluating machine translation systems are addressed.

Probabilistic finite-state machines are used today in a variety of areas in pattern recognition, or in fields to which pattern recognition is linked: computational linguistics, machine learning, time series analysis, circuit testing, computational biology, speech recognition and machine translation are some of them. In part I of this paper we survey these generative objects and study their definitions and properties. In part II, we will study the relation of probabilistic finite-state automata with other well known devices that generate strings as hidden Markov models and n-grams, and provide theorems, algorithms and properties that represent a current state of the art of these objects.

We introduce a novel decoding procedure for statistical machine translation and other ordering tasks based on a family of Very Large-Scale Neighborhoods, some of which have previously been applied to other NP-hard permutation problems. We significantly generalize these problems by simultaneously considering three distinct sets of ordering costs. We discuss how these costs might apply to MT, and some possibilities for training them. We show how to search and sample from exponentially large neighborhoods using efficient dynamic programming algorithms that resemble statistical parsing. We also incorporate techniques from statistical parsing to improve the runtime of our search. Finally, we report results of preliminary experiments indicating that the approach holds promise. 1

State-of-the-art machine translation techniques are still far from producing high quality translations. This drawback leads us to introduce an alternative approach to the translation problem that brings human expertise into the machine translation scenario. In this framework, namely Computer Assisted Translation (CAT), human translators interact with a translation system, as an assistance tool, that dinamically offers, a list of translations that best completes the part of the sentence already translated. In this paper, finite state transducers are presented as a candidate technology in the CAT paradigm. The appropriateness of this technique is evaluated on a printer manual corpus and results from preliminary experiments confirm that human translators would reduce to less than 25 % the amount of work to be done for the same task. 1

We describe a Bayesian inference algorithm that can be used to train any cascade of weighted finite-state transducers on end-toend data. We also investigate the problem of automatically selecting from among multiple training runs. Our experiments on four different tasks demonstrate the genericity of this framework, and, where applicable, large improvements in performance over EM. We also show, for unsupervised part-of-speech tagging, that automatic run selection gives a large improvement over previous Bayesian approaches. 1

statistical machine translation system follows a generative model of translation and is implemented by the composition of component models of translation and movement realised as Weighted Finite State Transducers. Our flexible architecture requires no special purpose decoder and readily handles the large-scale natural language processing demands of state-of-the-art machine translation systems. In this paper we describe the CUED system’s participation in the NIST 2008 Arabic-English machine translation evaluation task. Key words: Statistical machine translation, weighted finite state transducers, large-scale natural language processing, finite state grammars. 1

The automated translation of one natural language to another, known as machine translation (MT), typically requires successful modeling of the grammars of the languages and the relationship between them. Rather than hand-coding these grammars and relationships, some machine translation e#orts employ data-driven methods, where the goal is to learn from a large amount of training examples of accurate translations. One such data-driven approach is statistical MT, where language and alignment models are automatically induced from parallel corpora. This work has also been extended to probabilistic finite-state approaches, most often via transducers.

We present Minimum Bayes-Risk word alignment for machine translation. This statistical, model-based approach attempts to minimize the expected risk of alignment errors under loss functions that measure alignment quality. We describe various loss functions, including some that incorporate linguistic analysis as can be obtained from parse trees, and show that these approaches can improve alignments of the English-French Hansards.

Word graphs have various applications in the field of machine translation. Therefore it is important for machine translation systems to produce compact word graphs of high quality. We will describe the generation of word graphs for state of the art phrase-based statistical machine translation. We will use these word graph to provide an analysis of the search process. We will evaluate the quality of the word graphs using the well-known graph word error rate. Additionally, we introduce the two novel graph-to-string criteria: the position-independent graph word error rate and the graph BLEU score. Experimental results are presented for two Chinese–English tasks: the small IWSLT task and the NIST large data track task. For both tasks, we achieve significant reductions of the graph error rate already with compact word graphs.

State-of-the-art computer-assisted translation engines are based on a statistical prediction engine, which interactively provides completions to what a human translator types. The integration of human speech into a computer-assisted system is also a challenging area and is the aim of this paper. So far, only a few methods for integrating statistical machine translation (MT) models with automatic speech recognition (ASR) models have been studied. They were mainly based on N-best rescoring approach. N-best rescoring is not an appropriate search method for building a real-time prediction engine. In this paper, we study the incorporation of MT models and ASR models using finite-state automata. We also propose some transducers based on MT models for rescoring the ASR word graphs. 1