Скачати 27.9 Kb.
Зміст1. Samuelson-brown g.a.
Вісник ЛНУ імені Тараса Шевченка № ( ), 2011
O. A. Kyrychenko
Y. V. Kalashnyk
MAIN STRATEGIES IN FURTHER DEVELOPMENT OF MACHINE TRANSLATION. APPLICATION PROBLEMS
Different electronic devices have become common nowadays. Due to the fundamental research in the systems of algorithms and in the establishment of lexical equivalence in different strata of lexicon, machine translation has made considerable progress in recent years.
But nevertheless there is a problem: machine cannot correctly translate all grammatical phenomena and presently there is no such translator which could replace the person. Perhaps “machine translation” is not an appropriate term, since the machine only completes the first stage of the process. It would be more accurate to talk of a tool that aids the translation process, rather than an independent system.
The goal of this article is to find the last strategies in further development of machine translation; to mark the problems of its using and possible ways and perspectives of its development.
The achievement is that now there is a set of commercial projects of machine translation. Company Systran was one of pioneers in the field of machine translation. In Russia great contribution to the development of machine translation brought the group under the leadership of prof. R.G.Piotrovsky (Russian State Pedagogical University, St.-Petersburg).
The beginning of the 1990s saw vital developments in machine translation with a radical change in strategy from translation based on grammatical rules to that based on bodies of texts and examples (for example, the Reverso Program) [1, p. 15]. Language was no longer perceived as a static entity governed by fixed rules, but as a dynamic corpus that changes according to use and users, evolving through time and adapting to social and cultural realities. To this day machine translation continues to progress. Large companies are now using it more, which also increases software sales to the general public. This situation has led to the creation of on-line machine translation services such as Altavista, which offer rapid email services, web pages, etc. in the desired language, as well as to the availability of multilingual dictionaries, encyclopaedias, and free, direct-access terminology databases.
Until recent times, the production of translations has been seen essentially as a self-contained activity. For large users, the appearance of translation systems has stimulated the integration of translation and documentation (technical writing and publishing) processes. Translation is now seen as one stage in the processes of communication and getting information.
Presently there are many researches of machine translation, sets of presentations on this theme, for example, Powerpoint Presentations like Presentation at the conference “Current issues in theoretical and applied linguistics”, 11 December 2007,Челябинск Chelyabinsk,, РоссияRussia29. Слайдов. [PDF, (29 slides), [2, p. 5] or Presentation on panel held at Aslib conference “Translating and the Computer 30”, 27 November 2008 [3, p. 2].
Machine translation is an autonomous operating system with strategies and approaches that can be classified as follows [4, p.54] :
The direct strategy, the first to be used in machine translation systems, involves a minimum of linguistic theory. This approach is based on a predefined source language-target language binomial in which each word of the source language syntagm is directly linked to a corresponding unit in the target language with a unidirectional correlation, for example from English to Spanish but not the other way round [5, p. 51]. The best-known representative of this approach is the system created by the University of Georgetown, tested for the first time in 1964 on translations from Russian to English. The Georgetown system, like all existing systems, is based on a direct approach with a strong lexical component. The mechanisms for morphological analysis are highly developed and the dictionaries extremely complex, but the processes of syntactical analysis and disambiguation are limited, so that texts need a second stage of translation by human translators.
There are a number of systems that function on the same principle: for example SPANAM, used for Spanish-English translation since 1980, and SYSTRAN, developed in the United States for military purposes to translate Russian into English. After modification designed to improve its functioning, SYSTRAN was adopted by the European Community in 1976. At present it can be used to translate the following European languages:
Source languages: English, French, German, Spanish, Italian, Portuguese, and Greek.
Target languages: English, French, German, Spanish, Italian, Portuguese, Greek, Dutch, Finnish, and Swedish.
In addition, programs are being created for other European languages, such as Hungarian, Polish and Serbo-Croatian.
Apart from being used by the European Commission, SYSTRAN is also used by NATO and by Aйrospatiale, the French aeronautic company, which has played an active part in the development of the system by contributing its own terminology bank for French-English and English-French translation and by financing the specialized area related to aviation. Outside Europe, SYSTRAN is used by The United States Air Force because of its interest in Russian-English translation, by the XEROX Corporation, which adopted machine translation at the end of the 1970s and which is the private company that has contributed the most to the expansion of machine translation, and General Motors, which through a license from Peter Toma is allowed to develop and sell the applications of the system on its own account. It should be noted that in general the companies that develop direct machine translation systems do not claim that they are designed to produce good final translations, but rather to facilitate the translator's work in terms of efficiency and performance.
The transfer strategy focuses on the concept of "level of representation" and involves three stages. The analysis stage describes the source document linguistically and uses a source language dictionary. The transfer stage transforms the results of the analysis stage and establishes the linguistic and structural equivalents between the two languages. It uses a bilingual dictionary from source language to target language [4, p. 22]. The generation stage produces a document in the target language on the basis of the linguistic data of the source language by means of a target language dictionary.
The transfer strategy, developed by GETA (Groupe d'Etude pour la Traduction Automatique / Machine Translation Study Group) in Grenoble, France, led by B. Vauquois, has stimulated other research projects. Some, such as the Canadian TAUM-MЙTЙO and the American METAL, are already functioning. Others are still at the experimental stage, for example, SUSY in Germany and EUROTRA, which is a joint European project. TAUM, an acronym for Traduction Automatique de l'Universitй de Montrйal (University of Montreal Machine Translation) was created by the Canadian Government in 1965. It has been functioning to translate weather forecasts from English to French since 1977 and from French to English since 1989. One of the oldest effective systems in existence, TAUM-MЙTЙO carries out both a syntactic and a semantic analysis and is 80% effective because weather forecasts are linguistically restricted and clearly defined. It works with only 1,500 lexical entries, many of which are proper nouns. In short, it carries out limited repetitive tasks, translating texts that are highly specific, with a limited vocabulary (although it uses an exhaustive dictionary) and stereotyped syntax, and there is perfect correspondence from structure to structure.
The pivot language strategy is based on the idea of creating a representation of the text independent of any particular language. This representation functions as a neutral, universal central axis that is distinct from both the source language and the target language. In theory this method reduces the machine translation process to only two stages: analysis and generation [6, p. 12]. The analysis of the source text leads to a conceptual representation, the diverse components of which are matched by the generation module to their equivalents in the target language. The research on this strategy is related to artificial intelligence and the representation of knowledge. The systems based on the idea of a pivot language do not aim at direct translation, but rather reformulate the source text from the essential information. At the present time the transfer and pivot language strategies are generating the most research in the field of machine translation. With regard to the pivot language strategy, it is worth mentioning the Dutch DLT (Distributed Language Translation) project which ran from 1985 to 1990 and which used Esperanto as a pivot language in the translation of 12 European languages.
It is important, first of all, to make a distinction between machine translation (MT) and computer-assisted translation (CAT).
Often a source of confusion for the general public, where the term "computer translation" is used to describe both types of technology, the two are in fact based on very different approaches. The respective results they are intended to achieve are also extremely different, since they use two quite separate, specific contexts.
On a schematic level, this method of translating involves the calculation speed of a computer in order to analyse the structure of each term or phrase within the text to be translated (source text). It then breaks this structure down into elements that can be easily translated, and recomposes a term of the same structure in the target language [7, p. 174]. In doing so, the method calls upon the use of highly voluminous, multi-lingual dictionaries plus sections of text that have already been translated.
Great hopes were placed in MT during the eighties, and huge investments were made in research into the subject. However, this was then to a large extent neglected in favour of CAT systems that were technically more realistic. Thanks to the development of the Internet over recent years, there is now a move towards both sites, and automatic translation systems, that make it possible to "get an idea" of the content of pages written in another language.
Apart from this function of providing a rough idea of what a given text contains and its utility when deciding whether not this would be worth translating, MT is only efficient where applied to texts with an appropriate degree of standardisation and coherency. In short, a text that can be translated by a computer must be written in a way that the computer can understand: there must be no ambiguity, and it must contain only terms contained in the computer's dictionary and which always have the same meaning.
This type of controlled language - which imposes major constraints on writers - has few areas of use beyond that of particular types of technical documentation that are sufficiently voluminous to justify the investment.
The best-known, and perhaps the most efficient of all MT systems is used in Canada for translating weather forecasts from English into French and vice-versa. These are created from a highly limited, self-contained unit of standard phrases.
Otherwise, MT is mainly used for a pre-translation phase that must be followed by intensive revision process in order to make the target text suitable for publication.
The extremely high costs of setting up and managing parameters for MT software and its dictionaries are a major obstacle with automatic translation.
So, machine translation is the application of computers to the task of translating texts from one natural language to another. One of the very earliest pursuits in computer science, machine translation has proved to be an elusive goal, but today a number of systems are available which produce output which, if not perfect, is of sufficient quality to be useful in a number of specific domains.
In perspectives, machine translation is only efficient where applied to texts with an appropriate degree of standardization and coherency. In short, a text that can be translated by a computer must be written in a way that the computer can understand: there must be no ambiguity, and it must contain only terms contained in the computer’s dictionary and which always have the same meaning.
^ Practical Guide for Translators (2nd Ed.) / G. A. Samuelson-Brown // London: Multinqual Mattersltd, 1995. - 220 p. 2. Current issues in theoretical and applied linguistics / Chelyabinsk,, РоссияRussia, 29. Слайдов. [PDF, 2007. – 30 p.Челябинск 3. Presentation on panel held at Aslib conference / Translating and the Computer 30 // London, 2008. – 20 p. 4. Hutchins W.J. Machine Translation: Past, Present, Future. Wiley / W.J. Hutchins, Chichester, Ellis Horwood // New York, 1986. - 120 p. 5. POUDAT, Celine La traduction automatique en libre acces sur I’Internet // Le franзais dans le monde. – 2001. № 314 - P. 51-52. 6. Cohen J.M. Translation, Encyclopedia Americana / J. M. Cohen // New York, 1986. - P. 12-15. 7. First and most notably Bar-Hillel, Yeheshua: A demonstration of the nonfeasibility of fully automatic high quality machine translation in language and information; selected essays on their theory and application // Jerusalem Academic Press, 1964. - P. 174-179.
O. A. Kyrychenko
Y.V.Kalashnyk Main strategies in further development of machine translation. Application problems
This article is about machine translation. It describes the technology available to translators in this first decade of the twenty-first century and examines the negative and positive aspects of machine translation and of the main tools used in computer-assisted translation: electronic dictionaries, glossaries, terminology databases, on-line bilingual texts.
Keywords: machine translation, translators, dictionaries, glossaries, texts.
Калашник Ю.В. Головні стратегії подальшого розвитку машинного перекладу. Можливі проблеми
Стаття присвячена розгляду машинного перекладу. У ній описуються технології, сприятливі для перекладачів у першолу десятиріччі двадцять першого століття та досліджуються позитивні та негативні аспекти машинного перекладу та головних інструментів, які використовуються в ньому: електронні словники, глосарії, термінологічні бази даних, двомовні он-лайн тексти.
^ машинний переклад, перекладачі, словники, глосарії, тексти.
Калашник Ю.В. Главные стратегии в дальнейшем развитии машинного перевода. Возможные проблемы
В статье рассматривается машинный перевод. В ней описываются технологии, благоприятные для переводчиков в первом десятилетии двадцать первого века, а так же исследуются позитивные и негативные аспекты машинного перевода и главных инструментов, которые используются в нем: электронные словари, глоссарии, терминологические базы данных, двуязычные он-лайн тексты.
Ключевые слова: машинный перевод, переводчики, словари, глоссарии, тексты.
|Application form of participant of the X international scientific-practical conference “Methodological problems of modern translation”||Application form to take part in the|
«Actual problems of industrial economy and logistics development» organizing committee
|Application form ХІІІ international scientific conference «Ideas of Academician Vernadskyi, Problems of Research and Evaluation of Regional Sustainable Development»|
«Ideas of Academician Vernadskyi, Problems of Research and Evaluation of Regional Sustainable Development»
|Application for participation in the International Conference «Financial system of Ukraine: problems and perspectives of development within social and economic transformations»|
«Financial system of Ukraine: problems and perspectives of development within social and economic transformations»
|Machine translation||Machine translation|
|Application form ХV international scientific conference «Ideas of Academician Vernadskyi and Problems of Regional Sustainable Development»|
«Kremenchuk Plavni». The conference fee does not cover meals and accommodation. For foreign participants the conference fee may be...
|Application form ХІV international scientific conference «Ideas of Academician Vernadskyi, Problems of Research and Evaluation of Regional Sustainable Development»|
«Kremenchutski Plavni». The conference fee does not cover meals and accommodation. The conference fee for foreign participants may...
|Methods of pathophysiological investigations. Main stages of pathophysiology as a science development. Actuality of the theme||Ínfocommunications: Problems and Prospects of Development” Odessa, Ukraine, 8 – 10 September 2010|