《Machine Translation Trends and Problems1.doc》由会员分享，可在线阅读，更多相关《Machine Translation Trends and Problems1.doc（23页珍藏版）》请在三一办公上搜索。
1、机器翻译：趋势与问题Machine Translation: Trends and ProblemsContentsAbstract.1Key words.1Preface.2I. Introduction.31.1 What is Machine Translation? .31.2 Historical background.3II. The Actuality of Machine Translation Home and Abroad.42.1 Trends exist in Machine Translation. 42.2 Types of translation demand.5
2、III. The choosing and improving of Machine Translation systems and softwares.73.1 How to choose an applicable software or system.73.2 Examples of the productions of some softwares and systems.83.2.1 Simple sentences translating83.2.2 Complex sentences translating .93.2.3 Two examples of good transla
3、tion .113.2.4 Paragraph and passages translating .113.2.4.1 Technology material.113.2.4.2 Literature article .133.3 Analysis of the productions of these Machine Translation softwares and systems . .163.4 How to use these systems and softwares.173.5 How to ameliorate these systems and softwares.183.5
4、.1 The application of symbolic logic on eliminating different meanings. .183.5.2 Analysis of language environment.183.5.3 The application of emotion analysis and probability computing .183.5.4 The designing of special lexicon .193.5.5 The designing and application of controlled language. .193.5.6 Mo
5、dularizing designing for corpus . .20IV. Trends of Machine Translation development .20V. Conclusion . .21References.21Machine Translation: Trends and Problems摘要: 随着改革开放的深入特别是在加入世界贸易组织以后，中国的国际化步伐正在逐步加快，对外交流与合作逐渐加强，而外语人才的供应远不能满足需要。外语人才的培养需要一定的周期，所以在计算机出现以后人们设想把机器用于翻译领域，也就是人们所熟知的机器翻译。五十多年以来，尽管机器翻译取得了很大
6、的突破，但是当今的机器翻译系统和软件在大多数领域还达不到足够水平来满足人们的各种需求。本文在分析了当前翻译系统和软件的基础上，阐述了目前机器翻译所存在的问题，以及在当前条件下给出一些建议来更好地使用目前的机器翻译系统和软件的作用，探讨机器翻译的发展趋势。关键词：机器翻译；问题；改进；趋势Abstract: With the deepening that our country reforms and opens up to the outside world especially after join into the WTO, the internationalized paces of C
7、hina are being accelerated progressively. The international exchange and cooperation in China is being strengthened gradually, while the supply of interpreters and translators can not satisfy the demand. To train interpreters and translators needs aptotic cycle, so people tried to use the machine to
8、 do translating since the first computer appeared, which is so called machine translation that known by people. More than 50 years past, though engineers have made very great break-through in machine translation, current machine translation systems and softwares can not satisfy various demands of hu
9、man being. This text will talk about the problems that current machine translation exists base on the analysis of some translation systems and softwares, and suggest that how to use machine translation systems and softwares better under present condition, and discuss the development trends of machin
10、e translation.Key words: Machine Translation；problems；ameliorating；trends PrefaceChinas rapid economic growth has put the country in the globe spotlight, and has made overseas countries greatly interested in China, the amount of books introduced to China greatly outnumbered and China as one of the o
11、ldest countries in the world attracts to the world people, but limited knowledge and language barriers have been the major hurdles for foreigners to know more about China. At this point, the language barrier still exists, moreover, along with the whole world economic integration development, the lan
12、guage exchange barrier has become the bottleneck among the countries in communication. Although full time personnel massively emerges in the translation domain, if still could not satisfy the translation market demand which is inflated day by day, whether or not some kind of multi-purpose machine co
13、uld replace the artificial translation, was made the Machine Translation research enter once again into peoples line of sight.First, Machine Translation has become the intermediate stage between the countries communication, it has formed a research and the development Machine Translation system upsu
14、rge in the world scope, the large-scale market demands facilitated this upsurge. The violent development of Internet makes the information and knowledge diffuse around the whole world, these information involve aspects of peoples work and daily life; but the personal computer rapid development and p
15、opularization, makes it possible for people to conveniently to distribute information to every place of the world through the Internet network server. In the Internet, most of the information exist as text written by individual natural languages, but it is impossible for average consumers to be fami
16、liar with many foreign languages, if one wants to browse a foreign language homepage, he or she needs to translate the homepage to the one written by their native language, thus they have the demand to the Machine Translation software or translation engineer online. Second, along with the economical
17、 globalization time arrivals, companys product must sell to world, the products technical documents should be translated to the local language. In addition, international organization and intergovernmental documents also need to use the many kinds of languages to write, in order to exchange informat
18、ion, the multinational corporation and the international organization favor the Machine Translation systems with high efficiency but low cost. Third, as long as the development of economic, more and more people have the capability to visit different countries where they have to communicate with the
19、local dwellers with than target language, therefore the language becomes the bottleneck, then a translation machine will break this bottleneck.I. Introduction1.1 What is Machine Translation? Machine Translation (MT) is the application of computers to the task of translating texts from one natural la
20、nguage to another.1.2 Historical backgroundSystems for automatic translation have been under development for 50 years in fact, ever since the electronic computer was invented in the 1940s there has been research on their application for translating languages (Hutchins 1986). For many years, the syst
21、ems were based primarily on direct translations via bilingual dictionaries, with relatively little detailed analysis of syntactic structures. By the 1980s, however, advances in computational linguistics allowed much more sophisticated approaches, and a number of systems adopted an indirect approach
22、to the task of translation. In these systems, texts of the source language are analysed into abstract representations of meaning, involving successive programs for identifying word structure (morphology) and sentence structure (syntax) and for resolving problems of ambiguity (semantics). Included in
23、 the latter are component programs to distinguish between homonyms (e.g. English words such as light, which can be a noun, and adjective or verb, and solution, which can be a mathematical or a chemical term) and to recognize the correct semantic relationships (e.g. in The driver of the bus with a ye
24、llow coat). The abstract representations are intended to be unambiguous and to provide the basis for the generation of texts into one or more target languages. There have in fact been two basic indirect approaches. In one the abstract representation is designed to be a kind of language-independent i
25、nterlingua, which can potentially serve as an intermediary between a large number of natural languages. Translation is therefore in two basic stages: from the source language into the interlingua, and from the interlingua into the target language. In the other indirect approach (in fact, more common
26、 approach) the representation is converted first into an equivalent representation for the target language. Thus there are three basic stages: analysis of the input text into an abstract source representation, transfer to an abstract target representation, and generation into the output language.Unt
27、il the late 1980s, systems of all these kinds were developed, and it is true to say that all current commercially available systems are also classifiable into these three basic system types: direct, interlingual and transfer. The best known of the MT systems for mainframe computers are in fact essen
28、tially of the direct translation type, e.g. the Systran, Logos and Fujitsu (Atlas) systems. They are however improved versions of the type; unlike their predecessors, they are highly modular in construction and easily modifiable and extendable. In particular, the Systran system, originally designed
29、for translation only from Russian into English, is now available for a very large number of language pairs: English from and into most European languages (French, German, Italian, Spanish, Portuguese), Japanese, Korean, etc. Logos, originally marketed for German to English, is also now available for
30、 other languages: English into French, German, Italian and Spanish, and German into French and Italian. The Fujitsu ATLAS system, on the other hand, is still confined to translation between English and Japanese (in both directions).Among the most important of the mainframe transfer systems was METAL
31、, supported for most of the 1980s by Siemens in Germany. However, it was only at the end of the decade that METAL came onto the market, and sales were poor. During the 1990s, rights to METAL have been transferred to two organisations (GMS and LANT) in a complex arrangement. But the best known system
32、s adopting the transfer approach were research projects: Ariane at GETA in Grenoble, an MT project going back to the 1960s, and Eurotra funded by the Commission of the European Communities. There were hopes that Ariane would become the French national system, and there were plans to incorporate it i
33、n a translators workstation for Eurolang (see below), but in the end nothing came of them. As for Eurotra, it was undoubtedly one of the most sophisticated systems, but after involving some hundred of researchers in most countries of Western Europe for almost a decade, it failed to produce the worki
34、ng system that the sponsors wanted. It had been hoped that Eurotra would eventually replace the Systran systems that the Commission had acquired and was developing internally. In the late 1980s, Japanese governmental agencies began to sponsor an interlingua system for Asian languages, involving co-o
35、peration with researchers in China, Thailand, Malaysia and Indonesia. However, this project too has so far not produced a system after a decade of work. (For surveys of MT research and development in 1980s and early 1990s see Hutchins 1993, 1994.)II. The Actuality of Machine Translation home and abr
36、oad2.1 Problems in Machine Translation As translators, the workers will do their job base on their bilingual knowledge. They will analysis the source language with the background knowledge of culture, history, geography, customary usage and so on, and then reassemble the language form the target lan
37、guage. At the same time they have to pay attention to the language environment, human emotion, the underline meaning, hyper-language and so on, and the worker will filtrate the valuable information while delete the unnecessary information. Whereas, the computer is compound with one CPU, RAM and the
38、structure of data bus, they woke under the controlling of CPU by opening and closing of circuit in phase. No matter how fast the CPU run, it can only manage on order once. In addition, the CPU has no consciousness, no value judgment, no felling, so it cannot “understand” what is the real meaning of
39、mans words deeply. If we want to solve this trouble, we have to fix many enough CPUs, and we have to design a profuse corpus that contains minute linguistic knowledge, such as morphology, syntax, semantics, and pragmatics and so on to restrict the natural language.At the beginning of Machine Transla
40、tion appeared, most people worried that one day machine will take the place of personal translators, but under we discuss: the machine is the product of human brain, therefore it is possible that machine can replace part of human brain work on translating, although Machine Translation experienced mo
41、re than 50 years development, and also has obtained considerable development, the quality of the productions of Machine Translation problems as the bottleneck still exists as before.The experts home and abroad have been researching since the Machine Translation was invented, and the many dissertatio
42、ns on Machine Translation were published, the following are parts of them: Studies of Sci-Tech Translation Feng Zhiwei Professor Feng is the expert on Machine Translation, he wrote more than 100 disquisitions about Machine Translation, and he joined to design some Machine Translation systems, he was
43、 said to be this savant in the field. In this book Studies of Sci-Tech Translation he introduces the history of Machine Translations development, the advanced research and gives some suggestions to help people to use Machine Translation soft wares and systems, and in order to help human being resear
44、ch information on Internet, he introduces some famous and helpful webs and engines online. 2.2 Types of translation demandWhen giving any general overview of the development and the use of Machine Translation (MT) systems and translation tools, it is important to distinguish four basic types of tran
45、slation demand. The first, and traditional one, is the demand for translations of a quality normally expected from human translators, i.e. translations of publishable quality whether actually printed and sold, or whether distributed internally within a company or organisation. The second basic deman
46、d is for translations at a somewhat lower level of quality (and particularly in style), which are intended for users who want to find out the essential content of a particular document and generally, as quickly as possible. The third type of demand is that for translation between participants in one
47、-to-one communication (telephone or written correspondence) or of an unscripted presentation (e.g. diplomatic exchanges.) The fourth area of application is for translation within multilingual systems of information retrieval, information extraction, database access, etc.The first type of demand illustrates the use of MT for dissemination. It has been satisfied, to some extent, by Machine Translation systems ever
