VICTOR Translator is a computerized system for the automatic translation of English into Spanish, developed by MTC Soft, a small software firm in Granada, Spain.
Q: What was your role in the development of VICTOR?
A: Project manager, as well as analyst and programmer.
How many people worked on the project?
The linguistic analysis is the work of the promotor of the idea, a profesional translator from the European Commission with more that 20 years of experience.
In the development of the program, besides the project director there were two analyst-programmers working during the whole process both on the program and the dictionaries, along with the translator herself. Then there were 30 students and six professors from the Faculty of Translation and Interpretation from the University of Granada who created the first versions of the dictionaries, plus six students in practice to complete and aliment the dictionaries.
How long did it take you to reach the beta stage?
The linguistic analysis goes back 10 years. The first design of the application took about a year.
The creation of the dictionaries (both the program and the content) another year. It was another year’s work after the dictionaries before we launched the beta program. We’re still working on both of those aspects. To sum up, the overall project took 10 years, the last three and a half of which were dedicated to the development of the application.
Could you explain to us a little bit about the process of creation of this machine translator? What were the most difficult problems to overcome? What were the most unpleasant surprises you came up against in the process?
The principal problem that has to be overcome when making an automatic translator is the linguistic analysis, which the translator had already resolved.
For us the biggest challenge was to convert her analysis, in natural language, into computer language, that is to say, a program. Our main work was to develop a computer platform capable of converting the sub-processes of translation into computer routines. Once that platform was created, the difficulty lay in understanding those routines in natural language (which are mental processes) and put them down in lines of code (computational processes).
Our surprises have been the continuous changes which the translator has made in some of the phases of translation in order to improve them. The results of her work have been very valuable in checking the validity of the process, and have given rise to numerous adjusments.
What does VICTOR Translator that the others don’t?
VICTOR does a profound linguistic analysis of the text, backed up by a set of dictionaries which are very complete, classified by glossaries (by themes), and which are continually being nurtured with new concepts, and syntactical and semantic structures.
And how did you manage that?
Thanks to the initial linguistic analysis, and to the made-to-order dictionaries and to the computer platform we created to codifiy the translation processes.
What types of clients do you expect for VICTOR Translator? That is to say, who needs VICTOR?
I would say that, in the first phase it will be companies which need to translate large quantities of documents related to a concrete subject with its own glossaries.
Then there will be translators who require a previous analysis of the document they must translate or a first draft so as to be able to rework it a bit rather than starting from zero. Later on, when we’ve created enough glossaries, VICTOR will do the job for any person who needs rapid and trustworthy translations.
¿VICTOR Translator offers applications which go beyond simple machine translation, doesn’t it? What might these be?
R: Linguistic labelling of texts. Memories of translations. Semantic searches. Text classification. Support for translators.
I’d like to present a challenge to VICTOR Translator right here and now. Would it be capable of translating, “hand on hand,” a text at random, so as we can compare it with the translation of the same text made by one of the popular machine translators, say Google Translator?
This is the paragraph which we used for the demo, and the result was very good, first the text in the original English, then the Google translation, then VICTOR’S:
“Eurostat, in its press release, stated that it was not in a position to certify the figures included in the notification of Portugal, due, among other reasons, to shortage of information on capital injections from the Portuguese government to public corporations,which had been treated as acquisition of shares and other equities with no effect on the government deficit.”
“Eurostat, en su comunicado de prensa, declaró que no estaba en condiciones de certificar las cifras consignadas en la notificación de Portugal, debido, entre otras razones, a la escasez de información sobre las aportaciones de capital de que el Gobierno portugués a las empresas públicas, que había sido tratados como la adquisición de las acciones y otras, sin efecto sobre el déficit público.”
“Eurostat, en su comunicado de prensa, afirmó que no estaba en condiciones de certificar las cifras incluidas en la notificación de Portugal, debido, entre otras razones, a la escasez de la información sobre
las inyecciones de capital del gobierno portugués para las empresas públicas, que había sido tratada como la adquisición de las participaciones y otros valores sin efecto alguno en el déficit público.”