On the Road to Quality: Translation for the 21st Century
Federico Gaspari, Arle Lommel & Alan Melby
Tuesday, 25 March, 2014
Over the past 18 months, the QTLaunchPad project has defined a new flexible umbrella quality metric for human and machine translation, addressing the confusion and uncertainty associated with the measurement of both. This session will provide a summary of the QTLP project achievements, the roll-out of Multi-Dimensional Quality Metrics (MQM), and a review of approaches to human annotation and testing. This session will also look ahead to continued projects and innovation in the area of quality and technology improvements under QT21 and other research initiatives.
Federico Gaspari has a background in translation studies and holds a PhD in machine translation from the University of Manchester. He has more than 10 years’ experience as a university lecturer in specialized translation and translation technology in Italy and the UK. He is a postdoctoral researcher at the Centre for Next Generation Localisation at Dublin City University, specializing in translation quality evaluation as part of the QTLaunchPad project.
Arle Lommel is a senior consultant at the German Research Center for Artificial Intelligence (DFKI)’s Language Technology Lab in Berlin. At DFKI he works on standardization of translation-related metadata, translation quality, and other related projects. He is active in GALA’s Standards Initiative, representing GALA on various committees. The former director of open standards at LISA, he holds advanced degrees in linguistics and ethnography.
Alan K. Melby is Professor of Linguistics at Brigham Young University, where he is also the director of the Translation Research Group. He is active in ISO Technical Committee 37 and the American Translators Association. He is also chair of the Translation Technology Committee of FIT (the international federation of translators). His interest in translation technology dates back to 1970, when he started working on machine translation. Later, his interests have expanded to tools for human translators, philosophy of language, and translation-related standards.
Most machine translation output is fine for basic Western LSP needs, as they usually translate within European...
Machine translation is great when it works, but it fails often and in unpredictable ways. What causes bad machine...