Sometimes generic or raw machine translation doesn’t meet the requirements that have been placed to the translation and its quality. There are few options to overcome the situation. One is to lower the goals and requirements. Another option is to find more suitable machine translator. Third option is to post-edit the machine translation. Fourthly, one can choose to hire professional translator to do the translation starting from the beginning. Fifth option is to customize the machine translation in a way that it could reach the goals.
Machine translation is a hot topic all around the web. The tone of the discussion is often negative. Machine translation is argued to have such quality issues that the best it can produce are funny translation mistakes to laugh at. The jokes are amusing but overall we think that this kind of conversation has gone astray.
Machine translation is a tool for human beings. It is a machine to automate work that previously has been done by a man. It is created to make our lives easier. During the history there have been plenty of cases like this when a machine has been developed to ease the work of a man. Always there has been opposition against such innovations but when time has gone by these machines have found their places. This will happen to machine translation as well. And it is not a bad thing. Continue reading It Is Time to Stop Fighting Against Machine Translation and Start Finding Ways to Use It Most Efficiently
Translation quality is complex concept. Translation quality doesn’t work like an on-off switch. The complexity comes with the fact that translation quality is a continuum with rare extreme values and many causes. Here we list four of the reasons why a translation may have low quality.
The most important reason for translating any material is to share knowledge. Content is the king, and the king should be present also in the translation. In most translation cases it isn’t crucial to translate word by word as long as the actual message is being delivered correctly.
The translation quality is extremely low if the message has been changed during the translation process. However, one would have to compare the original and translated text to be able to see this type of error, and it really doesn’t require more than just a wrong word choice to distort the message.
The tone has a big impact on the translation quality. Depending on the type of the original text, the tone can be official, professional, humorous, easy-going, polite, informal etc. The writer of the original document has chosen certain tone for a reason and translators should respect this choice as much as possible.
Tone issues arise when the source and target languages have very different tone standards. For example the chosen pronouns can change the tone remarkably. It is not insignificant whether to use “you” or “You”, “tu” or “Lei”, “sinä” or “te”, “du” or “Sie” and so on. There are languages (and cultures) which have less strict rules on how to talk to other people. When the translation is made from this kind of “informal” language to more “formal” language there is a great risk of having a too impolite tone.
When a translation is made between two languages in most cases it is also made between two cultures and countries. Cultures include spoken and unspoken customs, like the use of colours, hand gestures and social norms, which need translators’ attention. Similarly different countries have different laws, regulations and other rules to follow.
For example if a product manual has instructions in case of an emergency, in order to localize the emergency number the translator should consider whether the reader is in Finland (112) or in USA (911) or in some other country. Likewise the translation should not courage people to break the law. Any translation which is not placed in the right context will be in low quality.
There is a reason why I put grammar to the last place on this list. To a certain level, grammar is not as important as it may seem. The thing is that grammar is usually the easiest thing to observe because it can be evaluated also when the original document is not available. This has lead to a custom of people focusing too much on small and marginal errors.
Grammar is a strong quality indicator to any native speakers, and any text with plenty of grammatical errors is relatively easy to label as low quality. On the other hand minor grammatical mistakes don’t matter when the goal is to deliver a message. Of course there are situations when misspellings and grammatical errors change the tone of the text and thus results low in the quality scale. But there are also places where the message is more important than the messenger.
|Free Ebook about Machine Translation Quality
This complete guide to machine translation and machine translation quality examines the topic through out and finds out the best practises to best quality. Get your free copy here!
It is usually very difficult to estimate or evaluate the quality of automatic translations. The main reason for this is that typically the user translates a piece of text either from or to a language that he doesn’t understand good enough. (If he did understand, then he wouldn’t need to translate it.) Thus he cannot really know whether the translation contains errors or not.
The traditional way to get an understanding of the machine translation quality has involved comparing the machine translation with a translation made by a professional translator. This has been done mainly for research and development purposes by the developers of machine translation technology. However, this kind of method is not useful in real-life situations because usually there isn’t available any professional translation for material which needs to be machine translated.
There is definitely a demand for a technology for automatic estimation of the quality of machine translations. The general idea behind such a technology would be creating a system which would automatically tell the user whether some machine translation is good or bad or something between. This kind of technology would benefit us in several ways:
- With reliable machine translation quality estimates automatic translations can be used in more demanding situations. Currently machine translation is often used for translating information where translations errors would cause only minimal or no harm at all. This has seriously limited the use of automatic translation.
- Bad translations can be filtered out of a post-editing process. The post-editing can be made more efficiently because the post-editor does not need the spend time with useless translations.
- Deciding whether the machine translation is good enough for publishing will become easier.
- The system can be used to select the best among several machine translations. This will obviously improve the overall perceived machine translation quality as well as avoid embarrassing mistakes.
Lately we at Multilizer have made significant steps in estimating machine translation quality automatically. The quality estimation will be also one of the subjects in a scientific workshop about machine translation in Montreal at the beginning of June.
|Localize your software efficiently with advanced Multilizer localization Tools. Free Trials available!|
In association with Kites, Finnish machine translation experts and enthusiasts have formed Special Interest Group for machine translation in Finland. In one meeting we handled a hot subject of post-editing machine translations. Post-editing means that a professional translator checks and edits automatic translations which are made by a machine. The interesting topic with excellent presentations (one made by Jukka Outinen of Lionbridge and another by freelance translator Tommi Nieminen) sparked a lively discussion.
One of the ideas highlighted during the meeting was that in traditional translation by a professional translator, it does not make much sense to lower one’s quality requirements. It does not improve productivity. A professional translator cannot choose to “write bad translations”. With professional translators, the style and fluency of the text come together with the translation. However, the situation is different when post-editing machine translations.
In post-editing machine translations it can make sense to lower quality requirements because that indeed improves productivity. When the task is to post-edit an automatic translation, the translator can choose not to correct those parts of the machine translation that are correct but written in a clumsy language. Thus the translator saves some time at the expense of the quality. Therefore, in post-editing machine translations the quality can indeed be traded for productivity.
This naturally changes the translation market. Clients can now choose between lower and higher quality, depending on his requirements and budget. Affordable, quick and good enough translations made by a machine and a man together are fulfilling the scale of available translation services. An increase in productivity will enlarge the entire translation industry.
|Automatic Translator for PDF Documents
You can translate your PDFs quickly with Multilizer. Save the translation into word document and post-edit the automatic translation easily. Download Free version here.