Word-level Alignment for Multilingual Resource Acquisition

TitleWord-level Alignment for Multilingual Resource Acquisition
Publication TypeReports
Year of Publication2002
AuthorsLopez A, Nossal M, Hwa R, Resnik P
Date Published2002/04//
InstitutionInstititue for Advanced Computer Studies, Univ of Maryland, College Park
Keywords*LEARNING MACHINES, *MULTILINGUAL RESOURCES, *WORDS(LANGUAGE), ACQUISITION, algorithms, ALIGNMENT, BENEFITS, ITERATIONS, LANGUAGE, linguistics
Abstract

We present a simple, one-pass word alignment algorithm for parallel text. Our algorithm utilizes synchronous parsing and takes advantage of existing syntactic annotations. In our experiments the performance of this model is comparable to more complicated iterative methods. We discuss the challenges and potential benefits of using the model to train syntactic parsers for new languages.

URLhttp://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA458782