Who dares refuse humanity is in continual change? Changes have always driven evolution and evolution is only accomplishable as abundant as innovations are encompassed by users, consumers…people at ample

After many years of development and research, machine translation has taken the floor and it’s worthy taking heed to what it has to state, or taking advantage of what it has to proffer why should we state MT is not worthy utilizing?  If so, we will be refutilizing all the arduous work technology experts and researchers have been executing for more than fifty years: in 1952, the first MT conference was kept at MIT (Massachusetts Institute of Technology). At that time, afloat automation of acceptable quality translation was considered as virtually hopeless and anthropoid intervention either before or after computer processes was thought to be substantive (Hutchins, 2001). Since then, much has been executed not only on the developers and researchers’ side, but also from the translators’ community, and it is time to expect for the big use of Machine Translation solutions

1 Why Choosing Machine Translation as Part of the Localization/Translation Process

Nowadays, MT technology and practices are altered. Some software developers or content   creators (much as Microsoft, IBM, just to name a few) have constructed their personal systems and sketched their personal guidelines to enforce it. The universal common has Google Translator Toolkit; and many language and technology companies have evolved their own customizable engines (such as Asia Online’s Statistical Machine Translation platform, Welocalize’s GlobalSight Technology, Systran’s Hybrid Machine Translation Engine, among others) to ply for an ample array of content types and carry through careful needs. By and ample, and in controlled-enough scenarios, machine translation helps clients reach foreign-language markets in shorter times and to an ampler scale. But, what is a controlled scenario? And what does it take? It encompasses a set of rules and procedures modulating and feeling MT post-editing; it takes, above all, experienced professionals in the technology and language areas, so that commonsense and adequate to quality goals are set, procedures are delimited accordingly, and pre and post-editing phases are admitted in the loop. Under such circumstances, MT can proffer an efficacious shortcut to multilingual communication

2 Tailoring Content for MT and Tailoring MT to Content

Once the decision of utilizing MT is made, a linguist or translation expert is substantive, either to make content fit for MT or to specify the best MTestablished approach established on content and destined use. As a get down point, content type and language utilized in the source text should be taken into account to select between statistical, rule-based or hybrid machine translation. Text intention is also applicable for making the decision, even on whether machine translation is possible or what type of post-editing will be necessitated. Linguists and developers working together will furnish the best outcome in terms of time and cost efficiencies, considering the translator’s input as the most utilitarian device to filter errors out, thus debarring the necessitate of continual corrections or heightening the engine. The role of the anthropoid translation editor and MT post-editor should be clearly separated. Post-editors have to be competent to focus on alining the MT output so that it reflects and conveys the meaning of the source text as accurately as accomplishcompetent (Krings, 2001). On the antonymous, human translation editors be given to endeavor to conceal the fact that the text has been interpreted (Senez, 1998)

3 Google Translator Toolkit – Free Machine Translation Engine

Both for the idiosyncratic and commercialised user, this product from Google offers a loose, easygoing to access and use of circular engine for machine translation. As a language service provider, we, at Ocean Translations S.R.L., have been utilizing this engine as the first translation step for several clients (only when specifically bespoken) and results were boosting. Our linguists, in their role of post-editors, are fulfilled with the quality they bring forth and the fees they get for it. It takes them one hour to post-edit 500-800 words (versus 800-1000 words redacted when translation was executed by another translator). A prolonged flow of work (tied in mainly to the long nature of much assignments) is also announced as one of the advantages of working as post-editors. As a moderate, around 650 words are post-edited per hour, and an eight-hour working day is accomplishable under post-editing working conditions, with borderline breaks in between, such as when working with anthropoid translation

As an illustrative fact, we have recently completed a job of more than 90,000 words post-edited and revised (English into Spanish) in 9 calendar days (from client’s confirmation to delivery) involving 1 project manager, 4 post-editors (one designated as a lead post-editor) and 2 reviewers, and estimated cost savings for the client were approximately 40%. As bespoken by one of our main and most valued translation clients, the Department of Reproductive Health and Research (RHR) at WHO Headquarters, we have transported out an analysis of changing over from the actual model (CAT Tool-based) to Google Translation Toolkit for the localization of the Reproductive Health Library, for which updates are brought forth every year. Our report to them clearly reflects our gross experience in relation to this engine, and it is boosting –although difficult, of course– to see how felicitous both parties can be with this solution, conveying time and money savings to one side, and a better utilization of resources and contracts for larger volume to the other.

4 Conclusion

As in any environment fear to change has to be overcome and collaborative alliances are the best tool for this. Machine Translation is no longer “the future” and it is here to stay. After many years of research and development, it has go an utilitarian tool accessible to the population at ample, which will yield the best results when utilized by the best developed and most measured up professionals: translators, terminologists and software developers. Any translation or localization endeavor has to be duly discoursed and a pros and cons analysis about utilizing MT should be executed by a team of language and technology professionals. In a nutshell, appending Machine Translation to the production cycle is an incontestable advantage, especially for large volume contents. Leveraging CAT and MT technologies with anthropoid post-editors, the translation industry may experience an earthshaking increase in its figures and it does not have to intend anthropoid professionals of the language industry will misplace their jobs on the antonymous, more and longer working opportunities may originate, as we have experienced, as translation becomes an easier and more elastic service to purchase

Abridged version of “Post-Editing Free Machine Translation: From a Language Vendor’s Perspective” presented at the AMTA 2010: the Ninth conference of the Association for Machine Translation in the Americas, Denver, Colorado, October 31 – November 4, 2010 Original Version can be found here

Ocean Translations is a global provider of high quality communications solutions, delivering expert language services across a broad range of sectors. Their nonrecreational services dwell of the postdating: Translation, Localization (L10N), Internationalization (I18N), Interpreting (synchronal, ordered and tele-interpreting), Transcription arduous copies and audio files, Multilingual DTP and Language and Cultural Training. Combining sound management and tracking ethics with linguistic teams specialised in both social localization and subject matter; Ocean Translations delivers articulate and efficacious language solutions (English, Spanish, Portuguese and Quechua) to serve an ample range of fields. As an ISO 9001:2008 attested organization, Ocean Translations teams postdate demanding processes in order to bring forth High-quality, culturally dead on target and timely-delivered translations

Article from articlesbase.com