Abstract not found

The paper focuses on the issues of establishing semantic content of syntactic structures via the contrastive study of the English and Russian language systems and parallel texts analysis for the tasks of machine translation. Particular attention is given to consideration of syntactic polysemy and ambiguity, and the mechanisms of polysemous structures presentation are proposed. The decisions are worked out on the basis of projecting the functional values through the traditional categorial meanings of language units and structures. The syntactic polysemy is understood as the immediate realization of more than one categorial head meaning within the same language structure. The phenomenon of syntactic polysemy determines the possible multiple transfer scheme for a given language pattern. The system of multivariant transfer rules is designed to be further specified by machine learning methods.

In order to simultaneously translate speech into multiple languages an extension of stochastic finite-state transducers is proposed. In this approach the speech translation model consists of a single network where acoustic models (in the input) and the multilingual model (in the output) are embedded. The multi-target model has been evaluated in a practical situation, and the results have been compared with those obtained using several mono-target models. Experimental results show that the multi-target one requires less amount of memory. In addition, a single decoding is enough to get the speech translated into multiple languages. 1

In this second part of the survey, we present the application of weighted extended topdown tree transducers in machine translation, which is the automatic translation of natural language texts. We present several formal properties that are relevant in machine translation and evaluate the weighted extended top-down tree transducer along those criteria. In addition, we demonstrate how to extract rules for an extended top-down tree transducer from existing linguistic data and how to obtain suitable rule weights automatically from similar information. Overall, the aim of the survey is twofold. It should provide a synopsis that illustrates how theory (tree transducers) and practice (machine translation) interact on this particular example. Secondly, it presents a uniform and simplified treatment of the rule extraction and training algorithms that is accessible to the nonexpert. Additional details can be found in the original results that are referenced throughout the text.

One of the approaches to statistical machine translation is based on joint probability distributions over some source and target languages. In this work we propose to model the joint probability distribution by stochastic regular bi-languages. Specifically we introduce the stochastic k-testable in the strict sense bi-languages to represent the joint probability distribution of source and target languages. With this basis we present a reformulation of the GIATI methodology to infer stochastic regular bi-languages for machine translation purposes. 1

Accurate and robust metrics for automatic evaluation are key to the development of statistical machine translation (MT) systems. We first introduce a new regression model that uses a probabilistic finite state machine (pFSM) to compute weighted edit distance as predictions of translation quality. We also propose a novel pushdown automaton extension of the pFSM model for modeling word swapping and cross alignments that cannot be captured by standard edit distance models. Our models can easily incorporate a rich set of linguistic features, and automatically learn their weights, eliminating the need for ad-hoc parameter tuning. Our methods achieve state-of-the-art correlation with human judgments on two different prediction tasks across a diverse set of standard evaluations (NIST OpenMT06,08; WMT06-08). 1

Abstract not found

probabilistic edit distance as predictions of translation quality. We learn weighted edit distance in a probabilistic finite state machine (pFSM) model, where state transitions correspond to edit operations. While standard edit distance models cannot capture long-distance word swapping or cross alignments, we rectify these shortcomings using a novel pushdown automaton extension of the pFSM model. Our models are trained in a regression framework, and can easily incorporate a rich set of linguistic features. Evaluated on two different prediction tasks across a diverse set of datasets, our methods achieve state-of-the-art correlation with human judgments.