Mirko Plitt


Qualitative Analysis of Post-Editing for High Quality Machine Translation
Frédéric Blain | Jean Senellart | Holger Schwenk | Mirko Plitt | Johann Roturier
Proceedings of Machine Translation Summit XIII: Papers

Productive Use of MT in Localization
Mirko Plitt
Proceedings of Machine Translation Summit XIII: Tutorial Abstracts

Localization is a term mainly used in the software industry to designate the adaptation of products to meet local market needs. At the center of this process lies the translation of the most visible part of the product – the user interface – and the product documentation. Not surprisingly, the localization industry has therefore long been an extensive consumer of translation technology and a key contributor to its progress. Software products are typically released in recurrent cycles, with large amounts of content remaining unchanged or undergoing only minor modifications from one release to the next. In addition, software development cycles are short, forcing translation to start while the product is still undergoing changes, so that localized products can reach global markets in a timely fashion. These two aspects result in a heavy dependency on the efficient handling of translation updates. It is only natural that the software industry turned to software-based productivity tools to automate the recycling of translations (through translation memories) and to support the management of the translation workflow (through translation management systems). Machine translation is a relatively recent addition to the localization technology mix, and not yet as widely adopted as one would expect. Its initial use in the software industry was for more accessory content which is otherwise often left untranslated, e.g. product support articles and antivirus alerts with their short lifecycle. The expectation had however always been that MT could one day be deployed on the bulk of user interface and product documentation, due to the expected process efficiencies and cost savings. While MT is generally still not considered “good” enough to be used raw on this type of content, it has now become an integral part of translation productivity environments, thereby transforming translators into post-editors. The tutorial will provide an overview of current localization practices and challenges, with a special focus on the role of translation memory and translation management technologies. As a use case of the integration of MT in such an environment, we will then present the approach taken by Autodesk with its large set of Moses engines trained on custom data. Finally, we will explore typical scenarios in which machine translation is employed in the localization industry, using practical examples and data gathered in different productivity and usability tests.


Connecting Writers and Translators - XML Based Content Management of Product Documentation at Autodesk
Mirko Plitt
Proceedings of Translating and the Computer 26


Resource alignment for machine translation or implicit transfer
Jean Senellart | Mirko Plitt | Christophe Bailly | Françoise Cardoso
Proceedings of Machine Translation Summit VIII

In this article we present the concept of “implicit transfer” rules. We will show that they represent a valid compromise between huge direct transfer terminology lists and large sets of transfer rules, which are very complex to maintain. We present a concrete, real-life application of this concept in a customization project (TOLEDO project) concerning the automatic translation of Autodesk (ADSK) support pages. In this application, the alignment is moreover combined with a graph representation substituting linear dictionaries. We show how the concept could be extended to increase coverage of traditional translation dictionaries as well as to extract terminology from large existing multilingual corpora. We also introduce the concept of "alignment dictionary" which seems promising in its ability to extend the pragmatic limits of multilingual dictionary management.

pdf bib
Evaluating the operational benefit of using machine translation output as translation memory input
Christine Bruckner | Mirko Plitt
Workshop on MT Evaluation

Following the guidelines for MT evaluation proposed in the ISLE taxonomy, this paper presents considerations and procedures for evaluating the integration of machine-translated segments into a larger translation workflow with Translation Memory (TM) systems. The scenario here focuses on the software localisation industry, which already uses TM systems and looks to further streamline the overall translation process by integrating Machine Translation (MT). The main agents involved in this evaluation scenario are localisation managers and translators; the primary aspects of evaluation are speed, quality, and user acceptance. Using the penalty feature of Translation Memory systems, the authors also outline a possible method for finding the “right place” for MT produced segments among TM matches with different degrees of fuzziness.