Although research has been conducted by several institutes on how to process written text for minority and vernacular languages, no academic research project thus far seems to have produced a usable, functional, authoring or translation tool for end-user native speakers of these types of languages. On the other hand, a set of software programs has been in the making for twenty years outside of academia.
On December 9, 1997, Digital Equipment Corporation and SYSTRAN A.G. launched AltaVista Translation Service, the first European language translation service for Web content. For the first time, non-English speaking users can translate information on the predominantly English speaking Web in real time.
Caterpillar is developing an Automatic Machine Translation (AMT) system for translating product support literature into eleven languages. Source language authors write in Caterpillar Technical English (CTE) which uses a constrained English language domain and sophisticated spelling, lexical, grammar and disambiguation software. CTE tools are accessed through pull down menus in the author's text editor. Integrating the source language author into the translations process using CTE has allowed the development of the AMT system which completely eliminates the need for human post-editing of the translated service literature.
Product life spans and documentation production times are becoming increasingly short and the expenditures for documentation are rising simultaneously with increasing product complexity. Hence, translation projects are becoming more costly as the parallel increasing documentation complexity.
It is not surprising that myths, half-truths, and misunderstandings abound regarding machine translation: It seems as if the experience most players in the translation field have with this technology does not go beyond toying a little with one of the free online translation tools. Almost every week, I come across an article informing its readers either that machine translation is and always will be a complete waste of time or that machine translation, while being a waste of time today, might actually be useful some time in the distant future. In the hope of setting the record straight, here is a closer look at some of the most common myths about machine translation.
The European Association for Machine Translation (EAMT) is an organization that serves the growing community of people interested in MT and translation tools, including users, developers, and researchers of this increasingly viable technology.
Machine translation often gives humorous translations or incorrect translations. Usually, a bad translation is because the source text is not clear in a way that a machine can 'understand'. If text is optimised for machine translation, machine translation gives excellent results. There are two sets of texts. The first set is written in standard English. The second set is equivalent to the standard English text, but it is optimised for machine translation. Google Translate was used to translate the texts into Bulgarian and into Spanish.
Many methods and measures for evaluating machine translation (MT) systems have been developed over the years. The ISLE project, funded jointly by the European Union and the US National Science Foundation, is continuing the work started in the EU's EAGLES project on systematizing these methods and measures.
Even if the attainable quality of automatic translation systems is insufficient under certain conditions, and despite careful preparation of the original text, nevertheless the translation provides a useful basis for a technical translator. The automatic translation greatly simplifies the production of a foreign language text and leads, all in all, to an efficient translation process. For example, the translation of a customer Website with the help of an automatic translation system (i.e. post-edited machine translation) cost us only a third of the time, which we had previously calculated as pure 'manual work'.
An article about machine translation was translated into Spanish by Google Translate (www.google.co.uk/language_tools?hl=en). In September 2009, professional translators evaluated the translation for fluency and for accuracy of meaning.
The mechanization of translation has been one of humanity's oldest dreams. In the twentieth century it has become a reality, in the form of computer programs capable of translating a wide variety of texts from one natural language into another. This book introduces methods adopted in current systems
One of the main concerns of internationalization consists of separating the main source code from the texts, the labels, the messages and all the other objects related to the specific language in use. This article briefly explain the TMX standard and a simple TMX Java bridge.
For many corporations, growing international is almost a must. Obviously, human translators play a key role in this difficult venture. A range of computer tools aimed at expediting the translation process are now being used by translators. However, whether or not translation tools are used, translators feel frustrated and blame technical writers for their flaws. Authoring does not seem to be done with translation in mind, and the linguistic issues to be solved up front are sometimes countless. An efficient, cost-effective, and high-quality translation requires the right combination of ingredients, and proper authoring will have a major impact on the entire process.
The purpose of this research is to compare several machine learning techniques on the task of Asian language text classification, such as Chinese and Japanese where no word boundary information is available in written text. The paper advocates a simple language modeling based approach for this task.
The easiest way to cope with existing language barriers undoubtedly is the use of translation programs, electronic helpers that translate texts automatically. However, with high expectations meeting poor quality translation results in the past, press media regularly concluded that users had better learn the language themselves or employ at least a human translator. Yet a closer look at modern machine translation (MT) programs allows a more subtle view.
Instead of 'translation', AltaVista offered me unbelievable junk, evidently, an unedited MT version of American promotional material. The text was unreal, the result of a myth: You click a button and the translation is staring at you. You are in the middle of a jungle.
Machine translation (MT) is the automatic translation of text using only software without the help of a human translator. An alternative name for machine translation is automated translation.
The demand by the global market for products which have been localized has brought a whole set of issues and concerns to international technical communication. Of particulur interest is the need to translate technical documentation into a number of languages without sacrificing the necessary timeto-market. Old solutions and processes are insufficient. This paper explores some of the computational tools now offered by the machine translation industry for the facilitation of multilingual document translation as modern corporations need it.
Machine translation, the use of computers for translating between languages, is only now coming of age, just at a time when there is increasing need for such technology. Views of machine translation range from realistic assessments to extravagant statements for and against the technology. The reality is that machine translation can provide high-speed automated quality translation depending on a variety of factors; it is not a panacea for all translation problems. Successful machine translation requires human-computer interaction which promotes the strengths of each. Machine translation has reached a stage at which it can contribute to multilingual technical communication.
The field of machine translation (MT) was the pioneer research area in computational linguistics during the 1950s and 1960s. When it began, the assumed goal was the automatic translation of all kinds of documents at a quality equalling that of the best human translators. It became apparent very soon that this goal was impossible in the foreseeable future.
Machine Translation is a wonderful technology partner for the technical communicator, saving, under the right circumstances, time and money. As with any partnership, roles, responsibilities, and accountability must be clearly defined. In this human-machine partnership, the technical communicator shoulders most of the responsibility. There are many translation systems available, and the one that is best for you can be identified by considering, among other things, the purpose of the translation, its audience, the document’s size, and the desired quality. Despite the sophistication of the systems currently on the market, a human translator is a requirement for most post-translation editing!
This chapter introduces the main concepts and methods used for machine translation systems from the beginnings of research in the 1950s until about 1990; it covers the main approaches of rule-based systems (direct, interlingua, transfer, knowledge based), and the principal translation tools; and it concludes with a brief historical sketch.
Machine translation is a sophisticated technology. However, it is not as sophisticated as human language. Understanding how MT works on the Web helps designers and developers prepare Web pages for MT. Preparatory tactics improve the usability of MT output.