Accession Number : ADA585928


Title :   Adding Statistical Machine Translation Adaptation to Computer-Assisted Translation


Descriptive Note : Final rept.


Corporate Author : ARMY RESEARCH LAB ADELPHI MD COMPUTATIONAL AND INFORMATION SCIENCES DIRECTORATE


Personal Author(s) : Winkler, Robert P ; Metu, Somiya ; LaRocca, Stephen A ; Morgan, John J


Full Text : http://www.dtic.mil/dtic/tr/fulltext/u2/a585928.pdf


Report Date : Sep 2013


Pagination or Media Count : 22


Abstract : Statistical machine translation (SMT) has proven effective for general purpose language translation but not for highly specialized domains like medicine, military operations, and law enforcement, which have their own technical jargon. We present a novel approach for iteratively incorporating a human translator in the loop to adapt SMT models to a particular domain. We show how these models can be made accessible via Web services and integrated with computer-assisted translation (CAT) tools. In this report, we describe a novel human-in-the-loop post-editing domain adaptation algorithm for refining SMT models using the Joshua decoder and integrate it with a CAT tool called OmegaT.


Descriptors :   *COMPUTER AIDED INSTRUCTION , *MACHINE TRANSLATION , *TRANSLATIONS , COMPUTER APPLICATIONS , LANGUAGE TRANSLATION , STATISTICS


Subject Categories : Linguistics
      Computer Programming and Software
      Statistics and Probability


Distribution Statement : APPROVED FOR PUBLIC RELEASE