User Dictionaries
Everyone uses words and phrases that, to them, have particular meanings. For example: parts lists, where a specific translation is required for an individual part description. Translution users can easily set up their own User Dictionaries, which control how the translation is handled. [Back to list]

Customer, Domain and Corporate Dictionaries
Translution Corporate users can also develop their own Domain dictionaries (for specialist subject areas or departments) and Corporate Dictionaries (for the organisation as a whole) which determine how specific words are translated and which can then be shared throughout the organisation. These dictionaries are available via the web, so that they are available and can be worked on anywhere. Translution's dictionaries are designed to be multi-lingual rather than bi-lingual. Using bi-lingual dictionaries, with just five languages, users would have to provide 20 entries (one for each language pair, in each direction). With multi-lingual dictionaries, only five entries need be provided. This considerably reduces the amount of coding that is required to develop dictionaries that can be used across a number of languages. [Back to list]

"Do Not Translate" lists
Translution provides a facility for the user to mark up text within a specific document that they do not want translated. It also provides Do Not Translate lists i.e. words which the user or the organisation would never want translated. Recent research undertaken by Professor Tony Hartley of the University of Leeds, shows that implementing Do Not Translate lists improves local translation accuracy by, on average, 23%. (Ref: Improving Machine Translation Quality with Automatic Named Entity Recognition, EAMT Workshop at EACL 2003 Budapest 13 April 2003). [Back to list]

Managing Already Translated Text
It is essential that already translated text is not re-translated as this reduces overall translation quality. This is important, particularly when replying to or forwarding emails across language barriers. Translution ensures this does not happen by always including the original text with the translated text, and by identifying already translated text in email replies and forwarded messages. Translution also ensures already translated web pages and documents are not re-translated. [Back to list]

Handling "Not Found Words"
Machine Translation (MT) engines are usually supplied with dictionaries of the most common words used in a language. However no MT engine could possibly include all the words in a language, particularly "rich" languages such as English, French and German. Until these words are translated and added to the dictionaries of MT engines held centrally, they will not be recognised by the translation engines and will simply pass through un-translated. As part of its ongoing commitment to improve translation quality, Translution collects and analyses all Not Found Words generated by all users and, after researching them, continuously adds selected new words and phrases to its dictionaries. We also add common idiomatic phrases and their translations. In this way overall quality of translation will be improved for all users of Translution products. [Back to list]

Specialised Dictionaries
We provide 20 specialised dictionaries covering the following areas which can be used automatically by selecting a dictionary profile. Easy to set up and used in conjunction with users own dictionaries these can have a dramatic impact on the accuracy of translation. Dictionaries are organised into 6 groups: Business, Colloquial, High Tech, Industrial, Military and Science. The individual dictionaries supported include: Automotive, Aviation/Space, Chemistry, Colloquial, Computers/Data Processing, Earth Sciences, Economics/Business, Electronics, Food Sciences, Legal, Life Sciences, Mathematics, Mechanical Engineering, Medicine, Metallurgy, Military Science, Naval/Maritime, Photography/Optics, Physics/Atomic Energy, Political Science. . [Back to list]

Dictionary Profiles
Users can use up to 10 dictionaries at any time organised in order of priority. We therefore enable users to set up a dictionary profile - a bit like setting up a style sheet - which when selected applies your rules of priority and which dictionaries are used automatically [Back to list]

[Back to top]

4.4  Using these tools, are the translation's accurate?

The translations accuracy is increased dramatically by using the provided tools.

[Back to top]

4.5  Do you have any tips on how we should write the source text in order to improve translation accuracy?

Our help guides and manuals (which can be downloaded from the website) also provide information on how to improve Translation accuracy.

Translution also runs comprehensive training courses which include modules on "Writing for Machine Translation". Please click here for further details.

[Back to top]

4.6  How important are the terminology dictionaries for improving both machine and human translation?

The more the Machine Translation engine understands your terminology, the more likely it is to provide an accurate Translation.

It's the same for human translation. Many companies have experienced poor human translations - usually because the translator doesn't understand your business and use of terminology. By building a multi-lingual terminology dictionary you can improve the human translation as well as the machine translation quite dramatically and the translations are also consistent. Translution's team of translators all use technology that allows them to import, use and update your terminology.

[Back to top]

4.7  What is Translation Memory and how is it used to improve both machine and human translation?

Translation Memory (TM) is source and target human translations stored and aligned into segments (usually sentences) in a database. Using TM for both machine and human translation ensures consistent and perfect translations of "standard phrases".

Storing, managing and using Translation Memory also can dramatically reduce the cost of translation by Translution's human translation teams as we do not offer discounts for matches over 75%

Source documents are scanned at Translution Central and compared with the translation memory database before they are presented to the translation engines. If a 100% match Translation memory is found this is used in preference to the machine translation.

[Back to top]

4.8  Does Machine Translation remove the need for expensive human translation?

For day to day communication and comprehension, Machine Translation does indeed remove the need for expensive human translation. Where translation accuracy must be assured i.e. for legal documents and marketing material and websites, human translation is still advised.

[Back to top]

4.9  Given that machine translation can never be as good as human translation, where should Translution be used?

Although Translution may not be as accurate as a human translator, the quality is indeed good enough to provide accurate comprehension of what is being communicated. Translution may be used in a large range of situations for example:

Personal communication,

Foreign travel - car hire, hotel reservations, ticket bookings,

Buying from abroad - eBay purchases, foreign suppliers

Own property abroad? - deal easily with banks, lawyers, estate agents

Business to Business Communication,

Increase overseas sales - remove the language barriers to trade

Find new products - buy from those suppliers that you couldn't deal with before

Improve internal communications - your employees may not all speak the same language

In summary, Translution can be used for:

Where it generally should not be used is in marketing communications (we define this as business to consumer where in this instance consumer is defined as somebody you don't have a relationship with) such as translating by machine your "brochure website". Translution provide organisations with their website translation service for this.

[Back to top]

4.10  You say that the Translution product will provide an automatic translation service. However I fail to see how this is true when you consider that users will have to use tools to improve translation quality.

Certainly users will have to customise their environment to see improvements in translation quality. However, the tools we have developed are very easy to use (mostly by clicking) and the need to use these tools will soon fall in the same way that the need to use a spell checker declines as it is used.

We also offer services which build the dictionaries and Do Not Translate lists for you.

[Back to top]

4.11  Can the software handle idiomatic phrases or is that something that can only be handled by a human translator?

Users can add idiomatic phrases that they use regularly to their dictionaries as fixed expressions, although we advise that you avoid using idiomatic expressions when you write as, without the use of a dictionary entry, the translations tend to be poor. We are also adding common idiomatic translations into Translution's dictionaries for the benefit of all our users.

[Back to top]

4.12  Which Machine Translation Engines are Translution using to provide translations?

Initially we are licensing a single machine translation engine from one of the leading companies in this sector (Systran). We will soon be integrating other machine translation engines to grow the number of languages we support.

We have also carefully evaluated six companies' machine translation engines and others are planned. Click here for more details.

Translution uses an "open architecture" and is "agnostic" to the machine translation engine used.

The benefits of having an "open architecture" are as follows:

[Back to top]