Electronic tools for translators in the 21st century

The International Journal of Translation and Interpreting Research

Recent years have witnessed the rapid development of translation technology, which has achieved tremendous success in both academia and industry. Due to these rapid advances, it is clear that technology has already profoundly affected the way translation is produced. More recently, translation technology – ranging from translation-specific technologies such as MT to more general-purpose speech technologies and cloud computing – calls into question some of the assumptions about how, by whom, and to what level of quality translation should be done. Commercially viable translation today is almost entirely the computer-aided variety, given the ubiquitous use of computers in text production practices (O’Hagan, 2020).

Proceedings of the 18th conference on Computational linguistics -, 2000

The Computing Research Laboratory is currently developing technologies that allow rapid deployment of automatic translation capabilities. These technologies are designed to handle low-density languages for which resources, be that human informants or data in electronically readable form, are scarce. All tools are built in an incremental fashion, such that some simple tools (a bilingual dictionary or a glosser) can be delivered early in the development to support initial analysis tasks. More complex applications can be fielded in successive functional versions. The technology we demonstrate has first been applied to Persian-English machine translation within the Shiraz project and is currently extended to cover languages such as Arabic, Japanese, Korean and others.

Communication & Language at Work, 2012

In this article three of the more common types of translation tools are presented, discussed and critically evaluated. The types of translation tools dealt with in this article are: Fully Automated Machine Translation (or FAMT), Human Aided Machine Translation (or HAMT) and Machine Aided Human Translation (or MAHT). The strengths and weaknesses of the different types of tools are discussed and evaluated by means of a number of examples. The article aims at two things: at presenting a sort of state of the art of what is commonly referred to as "machine translation" as well as at providing the reader with a sound basis for considering what translation tool (if any) is the most appropriate in order to meet his or her specific translation needs.

2017

This dissertation investigates the needs of professional translators regarding translation technologies with the aim of suggesting ways to improve these technologies from the users’ point of view. It mostly covers the topics of computer-assisted translation (CAT) tools, machine translation and terminology management. In particular, the work presented here examines three main questions: 1) what kind of tools do translators need to increase their productivity and income, 2) do existing translation tools satisfy translators’ needs, 3) how can translation tools be improved to cater to these needs. The dissertation is composed of nine previously published articles, which are included in the Appendix, while the methodology used and the results obtained in these studies are summarised in the main body of the dissertation. The task of identifying user needs was approached from three different perspectives: 1) eliciting translators’ needs by means of a user survey, 2) evaluation of existing ...

This article presents some of the results of an online survey that was carried out in order to identify professional translators’ requirements regarding translation technologies. Participants in the sample seem to show high interest in technologies, based the large number of participants who has received training in IT. Although machine translation (MT) is mainly ignored due to the low quality and big post-editing effort, most translators see a potential benefit in high quality MT. Translation Memory (TM) software, according to the users’ preferences, should be first of all intuitive, compatible with other tools and support a great variety of formats. Very few translators compile their own corpora, which is mainly because they are unfamiliar with suitable tools and techniques.

Machine Translation, 2005

The Language Translation Interface (LTI) is a prototype developed for the Australian Defence Organisation. The aim is to provide a single, simple, interface to a variety of MT tools and utilities for personnel who need to produce translations when they have no easy access to human translators. This paper describes the functionalities of the LTI and reports on our experience with users during development. The LTI has been demonstrated and trialled at several military exercises and the feedback received is now leading to the development of the Language Translation Tools Suite (LTTS) Keywords Translation tools • Multiple translations • Military users All trademarks are hereby acknowledged. All URLs last accessed between 15th and 16th February 2006.

Translation technologies constitute an important new field of interdisciplinary study lying midway between computer science and translation. Its development in the professional world will largely depend on its academic progress and the effective introduction of translation technologies in the translators training curriculum. In this paper different approaches to the subject are examined so as to provide us with a basis on which to conduct an internal analysis of the field of Translation technologies and to structure its content. Following criteria based on professional practice and on the idiosyncrasy of the computer tools and resources that play a part in translation activity, we present our definition of Translation technologies and the field classified in five blocks.

This paper describes the state of the practice for Human Translation (HT), the established tools, the research, and the capability gaps. The paper is a summary of the tutorial at the Association for Machine Translation of the Americas 2009 conference.

2011

Machine Translation (MT) has experienced remarkable improvements and consequently grown in popularity of late. It now functions not only as an end in itself but also as a valuable asset to be exploited by translators in the promising practice of post-editing the outcome of MT systems, which can yield faster and sometimes more accurate results. Most systems, however, were not originally designed having translators envisaged as potential users, which leaves a high demand for tools capable of catering for this new translation modality. With the purpose of showcasing what researchers and the industry have to offer in that respect, this study provides a review of a number of currently available translation tools from the perspective of translation post-editing. We have selected and described toolkits according to a set of criteria, highlighting main differences and similarities between them and also making mention of desirable features that have not been satisfactorily presented by any of the toolkits analysed.

2016

Kyiv national university of technologies and design, Kyiv Translation has undergone several stages in its development, but currently, the preference is given to informative translation in which the features of individual author's style are not so important. The development of information technology has resulted in computer programs to facilitate translation; we should know the advantages and disadvantages of this type of translation. Translation is a complex multifaceted phenomenon, some aspects of which may be the subject of study of different sciences. In the framework of translation studies one examines psychological, literary, ethnographic and other spheres of translation practice, as well as history of translation practice in a particular country or countries. But the main topic of my paper will be computer-assisted translation or computer-aided translation. And now it is important to make a distinction between machine translation (MT) and computer-assisted translation (CAT). On a schematic level, machine translation 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. In doing so, the method calls upon the use of highly voluminous, multilingual dictionaries plus sections of text that have already been translated [2]. Using a computer-assisted translation tool is a process which includes the use of software to aid individuals in translating. In case of time constraints, a computer-assisted translation tool can effectively reduce the translation time, enabling the translator to translate content in a timely manner [5]. The major distinction between MT and CAT lies with who is a primarily responsible for the actual task of translation. In MT, the computer translates the text, though the machine outputs may later be edited by a human translator. In CAT, translators are responsible for doing the translation, but they may make use of a variety of computerized tools to help complete this task and increase their productivity. Therefore, whereas MT systems try to replace translators, CAT tools support translators by helping them to work more efficiently [1, p. 4]. Humans and computers each have their strengths and weaknesses. The idea of CAT software is to make the most of the strengths of people and computers. Translation performed solely by computers has very poor quality. Meanwhile, no human can translate as fast as computer can. If we accept that translation demands total sensitivity to the cognitive aspects of a source text, it follows that a computer would need to understand language and assimilate facts in the way that humans do it in order to resolve textual ambiguity and create a version that paid due regard to semantic content and register. For example, an awareness of context is essential for the correct interpretation of a sentence such as visiting European dignitaries can be a nuisance. In translating this sentence, a human translator would take into account the sentences which preceded and followed, as well as the general context, the overall theme of the text and any relevant social, economic or cultural factors. However, a computers inability to acquire, comprehend and rationally apply real-world knowledge in this way does not render MT useless as a production tool. Raw MT output does not need to be perfect in order to be useful. Direct comparisons between a system's raw output and human translation are pointless; as MT is a production tool, its capacity to increase or speed up production, within acceptable cost parameters, is the only valid measure of its effectiveness. If its use can be shown to increase productivity and reduce costs, it is clearly advantageous; if it fails to de either, it is a white elephant [3, pp. 3-4]. By using a CAT tool, however, you can gain some of the speed, consistency and memory

cl.naist.jp

There have been proposed various techniques for combining machine translation (MT) and translation memory (TM) technologies in order to enhance retrieved TM matches and increase translators’ productivity. We provide an overview of these techniques and propose a way of classifying them. According to the results of our user survey, many translators are not aware of MT feature in their computer-assisted translation (CAT) tool. However, more than a half of the population perceive such combination as useful. We argue that it is necessary to take into account user perspective when evaluating MT and CAT integration and suggest characteristics of such evaluation.

Journal of Educational and Social Research

Nowadays we are all aware of the role that technology plays in our private and professional lives, as this has been and continues to be the purpose for which it was created and continues to develop. This article begins with a short analysis of the importance of the use of translation technology in various areas of modern life, focusing on the causes that led to its birth and development. It then describes in general terms the tools offered by this technology, from the translation machine to the computer-assisted translation, explaining what is considered to be the core of CAT known as MT – memory translation. In the last part, the article discusses the pros and cons of professional translators regarding the tools offered by this technology, concluding that on the one hand translators should increasingly insist on using these tools, to be competitive in translation’s process, but on the other hand also the companies that produce these technologies should work more towards the quality...

2010

This collection of scholarly articles asks the question How useful is translation technology? Pointing to the need for a widely used and reliable way to test the efficiency of language translation programs, the presenters show that commercial tools such as translation memories and translation workbenches are popular, and their developers find them useful in terms of productivity, consistency, or quality.

Machine Translation, 2004