Нугуманова М.А.

Карагандинский Государственный Университет

 им. академика Е.А. Букетова

 

Characteristics of machine and literature translations

 

The impact of the Internet has been significant in recent years. We are already seeing an accelerating growth of real-time on-line translation on the Internet itself. In recent years, we have seen many systems designed specifically for the translation of Web pages ("Pop-Up Dictionary", "Site Translator") and of electronic mail ("SKIIN"). The demand for immediate translations will surely continue to grow rapidly, but at the same time users are also going to want better results. There is clearly an urgent need for translation systems developed specifically to deal with the kind of colloquial (often wrongly formed and badly spelled) messages found on the Internet. The old linguistics rule-based approaches are probably not equal to the task on their own, and corpus based methods making use of the massive data available on the Internet itself are obviously appropriate. But as yet there has been little research on such systems. At the same time as we are seeing this growing demand for "crummy" translations, the Internet is also providing the means for more rapid delivery of quality translation to individuals and to small companies. A number of machine translation systems on the sale are already offering translation services, usually "adding value" by human post-editing. More will surely appear as the years go by.

However, the Internet is having further profound impacts that will surely change the future prospects for machine translation. There are predictions that the stand-alone PC with its array of software for word-processing, databases and games will be replaced by Network Computers which would download systems and programs from the Internet at any time as required. In this scenario, the one-off purchase of individually packaged machine translation software or dictionaries would be replaced by remote stores of machine translation programs, dictionaries, grammars, translation archives or specialized glossaries which would obviously be paid for according to usage. It is should be to said, that such a change would have profound effect on the way in which machine translation systems are developed.

Another profound impact of the Internet will concern the nature of the software itself. What users of Internet services are seeking is information in whatever language it may have been written or stored. Users will want a seamless integration of information retrieval, extraction and summarization systems with translation

In fact, it is possible that in a few years there will be fewer "pure" machine translation systems (commercial or on-line) and many more computer-based tools and applications in which automatic translation is just one component. As a first step, it will surely not be long before all word-processing software includes translation as an in-built option. Integrated language software will be the norm not only for the multinational companies but also available and accessible for anyone from their own computer (desktop, laptop, notebook or network-based server) and for any device like television or mobile telephone which interfacing with computer networks.

The most widely anticipated development of the next decade must be that of speech translation. When current research projects (ATR, C-STAR, JANUS, Verbmobil) were begun in the late 1980s and early 1990s, it was known that practical applications were unlikely before the next century. The limitation of these systems to small domains has clearly been essential for any progress, such are the complexities of the task; but these limitations mean that, when practical demonstrations are made, observers will want to know when broader coverage will be realizable. There is a danger here that the mistakes of the 1950s and 1960s might be repeated; then, it was assumed that once basic principles and methods had been successfully demonstrated on small-scale research systems it would be merely a question of finance and engineering to create large practical systems. The truth was otherwise; large-scale machine translation systems have to be designed as such from the beginning, and that requires many man-years of effort. It is still true to say that the best written-language machine translation systems of today are the outcome of decades of research and development.

Whatever the high expectations, it is surely unlikely that we will see practical speech translation of significantly large domains for commercial exploitation for another twenty years or more. Far more likely, and in line with general trends within the field of written language machine translation, is that there will be numerous applications of spoken language translation as components of small-domain natural language applications, e.g. interrogation of databases (particularly financial and stock market data), interactions in business negotiations or intra-company communication.

Prompt streams of an information exchange between the advanced industrial countries, the avalanche action of the scientific and technical documentation acting from manufacturers of the goods and current technologies, demand completely new approach to a problem of translation of the technical literature. An exit one: maximum to automate process, having left the person his creative editorial part. In it the machine translation system helps. Its parameters should meet four basic requirements:

• efficiency;

• flexibility;

• speed;

• accuracy.

Efficiency of machine systems is an opportunity of constant renewal of a lexicon and creation of new thematic dictionaries. In this parameter they considerably outstrip habitual typographical editions of various dictionaries.

Flexibility is an opportunity of «rough readjustments» on a concrete subject domain (for this purpose the specialized dictionaries serve) and "thin readjustments" on the concrete text, the book or group of documents (modified user dictionaries).

Speed - an opportunity of automatic input and processing of the text information from paper carriers. Only one system of optical input of texts (OCR-System) daily replaces more than ten class typists.

Accuracy - stylistically and grammatically correct adequate handing on of sense of the initial text on language of translation. This is the most "vulnerable" place of machine translation systems. However such obvious improvement of translation quality in late versions of machine translation systems, as for example, PROMT XT, installs confidence that soon the computer completely will take up all routine part of translation.

We have found out that machine translation is an effective means for viewing and information search in foreign language and this function is the main at work in Internet. Undoubtedly, means of machine translation never can catch all semantic nuances of the original text. Distinctions in syntax and semantics between western and east languages, - we shall tell English and Chinese - are too great for this purpose. Even adherent of machine translation recognize, that it is capable to transfer the basic essence of the document at the best.

In summary it would be desirable to emphasize, that the program - translator is, first of all, the tool which allows to solve problems of translation or to raise efficiency of work of the translator only in the event that it uses competently.

Bibliography

 

1.                      Бакулов А.Д., Леонтьева Н.Н. - "Теоретические аспекты машинного перевода". Радио и связь, М., 1990.

2.                      Беляева Л.Н., Откупщикова М.И. - "Прикладное языкознание" (Раздел - Автоматический (машинный) перевод). Изд-во Санкт-Петербургского ун-та, СПб.,  2001.

3.                      Леонтьева Н.Н. - "К теории автоматического понимания естественных текстов". Издательство Московского университета, М., 2000.

4.                      Нелюбин Л.Л. - "Компьютерная лингвистика и машинный перевод". ВЦП, М., 1991.

5.                      Hutchins W.J. - "Machine Translation: Past, Present, Future". "Wiley", Chichester, Ellis Horwood, N.Y. etc., 1986.