Tag Archives: machine translation

How to use machine translaton well

Machine Translation: 5 Top Tips for Using it Wisely

As a language services provider that relies on the expertise and experience of qualified human linguists and subject-area specialists, you might assume that we’d be firmly against the use of machine translation. However, that’s not the case. There’s certainly a time and place for machine translation and it can become a valuable and cost-effective ally for your business, but only if it’s used in the right way.

With that in mind, we thought it would be worthwhile providing a few tips about how machine translation can be used to enhance your business.

1. Use it sparingly

Numerous studies have found that Machine translation is not as accurate as human translation.. Machine translation struggles to translate words with multiple meanings accurately, it does not account for the tone of a translation, and it always translates literally and does not take cultural nuances into account. This leads to mistakes.

If you have a large amount of text that needs to be translated and accuracy is not important, or the translation is going to be worked on by a professional human translator at a later date, then machine translation could be the answer. Similarly, for non-consumer facing content where you just need to get the gist across, machine translation makes sense. In all other situations, you’d be wise to stay away.

2. Customise your machine translation engine

Customising the machine translation engine that you’re using will help to improve the accuracy of your translations. The customisation options available will differ depending on the platform you use. On some engines, you can upload translation memories with your desired translations for certain words, while others allow you to edit previous work so you can effectively ‘teach’ the platform to produce better translations.

3. Tailor your content

To get the best results from machine translation, it’s well worth taking some time to tailor your content to the algorithm’s strengths. You should remove any slang, colloquialisms, idioms and acronyms (unless they’re included in your terminology database) and avoid abbreviations such ‘i.e.’, ‘e.g.’ and ‘etc.’ You should also use short and simple sentences whenever possible, write in the active voice and avoid culturally specific information.

Here are a few more tips from IBM to help you tailor your content for machine translation engines.

4. Pay for post-editing from a human translator  

If the translation matters at all, please don’t release it to the world without thorough post-editing from a qualified linguist. Although machine translation has advanced greatly over the last five years, even the most sophisticated engines lack the nuanced understanding of language to be trusted entirely. If the end-product is destined for anything other than internal use, always get it checked by a human translator.

5. Use a quality language services provider 

We don’t want to blow our own trumpet, but there really is no substitute for our expert translation team. Whether you want to translate your marketing materials for an international audience or localise your product packaging for a new market, translation errors can undermine your brand and potentially carry a serious liability risk.

At Linguistica Translation and Recruitment, our team of professionally qualified translators, multilingual copywriters, editors, project managers and compliance experts are ready and waiting to produce first-class translations that your business can rely on.

For more information, please call 02392 987 765 or email info@linguistica-international.com today.

 

 

Human translators vs. machine translators

Can Machines Outperform Human Translators?

Ever since machine translation became neural machine translation in 2016, big tech has been trying to persuade us that it has reached human-level quality. Today, it has gone one step further. The nerds over in Silicon Valley are now trying to convince us that machine translation outperforms human-level translation. Are they right? Not on your nelly!

What exactly are the claims?

Anyone with knowledge of the industry knows that human translation has always been superior to machine translation in just about every way apart from speed and price. Big tech knows it, too. That’s why its claims are made with some interesting caveats.

The study only looks at whether a deep learning translation system called CUBITT can produce translations that are comparable to those produced by humans in the domain of ‘news’ translation, which accounts for a tiny proportion of the whole translation sector. The study also claims that machine translation only outperforms human translation in the metric of ‘adequacy’, but what exactly does that mean?

The sentence-level translation Turing test

The tests compared the work of CUBITT against human translators on almost 8,000 sentences across 53 documents. 15 human evaluators were then asked to rate the translations for ‘adequacy’.

The definition of adequacy for the purpose of the test was ‘adequately expressing the source text’s intended meaning in the target language’.

The human evaluators found that 52 percent of CUBITT’s sentences scored higher than the human translations when measured against this metric, while just 26 percent of CUBITT’s translations scored lower than sentences translated by humans. Impressive, right?

Here’s the catch

When compared to the work of human translators, the evaluators observed that CUBITT made fewer errors in addition of meaning, shift of meaning and omission of meaning. However, it made significantly more errors when it came to cross-sentence context and readability, with the work of the human translators rated as more fluent.

Interestingly though, another test compared 100 pairs of sentences that were translated by CUBITT and Google Translate. In this case, the evaluators found that CUBITT’s translations were less likely to be identified as the work of a machine when compared to those produced by Google Translate.

Better than Google Translate but still worse than humans

Big tech’s claims that CUBITT can outperform human translators seems to be more of a newspaper headline than a representation of reality, given that the metric of ‘adequacy’ is one that has been devised specifically for this test.

However, CUBITT can outperform fellow machine translation tool Google Translate, and that is something to celebrate. Machine translation undoubtedly has an important part to play in the industry, so any improvements are welcomed, but the truth is, there’s still no substitute for the work of a professional human translator.

Human translation from a leading UK team

At Linguistica International, our professional team of human translators can help you reach your customers in more than 250 languages. Get in touch to discuss your translation project today on 02392 987 765 or email info@linguistica-international.com.