Survey: Weighted Extended Top-down Tree Transducers Part II—Application in Machine Translation

Issue title: Non-Classical Models of Automata and Applications II

Article type: Research Article

Authors: Maletti, Andreas

Affiliations: Universität Stuttgart, Institute for Natural Language Processing, Azenbergstraße 12, 70174 Stuttgart, Germany. {andreas.maletti@ims.uni-stuttgart.de}

Note: [] Financially supported by the German Research Foundation (DFG) grant MA/4959/1-1 and the Ministerio de Educación y Ciencia (MEC) grant JDCI-2007-760 while the author was at: Universitat Rovira i Virgili, Departament de Filologies Romàniques, Avinguda de Catalunya 35, 43002 Tarragona, Spain Address for correspondence: Universität Stuttgart, Institute for Natural Language Processing, Azenbergstraße 12, 70174 Stuttgart, Germany

Abstract: In this second part of the survey, we present the application of weighted extended top-down tree transducers in machine translation, which is the automatic translation of natural language texts. We present several formal properties that are relevant to 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.

DOI: 10.3233/FI-2011-589

Journal: Fundamenta Informaticae, vol. 112, no. 2-3, pp. 239-261, 2011