Welcome / Bienvenue / Benvinguts / Bienvenidos
For information about my translation services, please visit the main site.
Pour des informations sur mes services, merci de regarder le site principal.
Para información sobre mis servicios de traducción, visite el web principal.

On the usefulness of machine translation (hear me out!)

Colleagues who know me know that I’m not a proponent of offering machine translation post-editing as a service. There is just so much to fix in a machine-translated text that it’s not a productive way of working, especially if you’re a perfectionist like me, who would find it to difficult to leave a sentence alone if the translation can be understood but could be improved.

Nevertheless, I don’t belong to the camp who believe that machine translation (MT) is never useful. In fact, I challenge anyone to tell me that MT would not save them time if they were translating the following sentence.

Continue reading


“Pain of the field” es lo de menos

Varios medios españoles y internacionales nos han ofrecido la noticia esta semana de que la web del Ministerio de Industria, Comercio y Turismo tiene una noticia en inglés sobre el nombramiento de un tal “pain of field” como miembro del Oficina Internacional de Pesas y Medidas. Este nombre raro es el resultado de la traducción automática del nombre de Dolores del Campo.

Una de las noticias más compartidas sobre el tema es bastante sorprendente: la de Euronews tiene un inglés muy deficiente, probablemente como resultado de una traducción automática.

Otra cosa que me ha sorprendido Continue reading


Machine translation and context

A sentence I’ve just translated is an excellent example of the advantages and disadvantages of machine translation. The original sentence said this:

Los rankings se basan en indicadores sociales y económicos.

Google Translate offered this:

The rankings are based on social and economic indicators.

This is a good example of how machine translation can speed up the translation process. The translation is almost perfect. I say almost, because the translation doesn’t quite work in my context. The reader is left asking “Which rankings?”.

The original sentence is actually talking about rankings in general, rather than any specific rankings. Unfortunately Spanish does not make this distinction in the use of articles, so the word “los” is needed whether talking about rankings in general or specific rankings referred to earlier in the text. Google Translate works sentence by sentence, so it has no way of knowing whether the word “the” should appear at the beginning of the English translation.

Another similar problem comes up when I translate biographical texts. Imagine a sentence in Spanish that says the following:

Nació en Tolosa en 1960, pero desde 1970 vive en Roma.

Is Tolosa referring to the city of Toulouse in the Languedoc region (Tolosa is the traditional Spanish spelling of the city) or the small town in the Basque Country? OK, so I’ve deliberately come up with an ambiguous place name, but the other problem in this example does occur more often: is the text talking about a male or female? Google Translate has no way of knowing, since it only looks at the context of the sentence. It normally chooses a sex seemingly randomly. In this particular example it has produced a translation that does not specified the sex of the person:

Born in Toulouse in 1960, but since 1970 living in Rome.

Although it has avoided assigning a sex to the person the text is talking about, the translation is unacceptable and would need considerable editing. By changing the sentence slightly I can force Google Translate to assign a sex:

Nació en Tolosa en 1960, pero desde 1970 vive con sus padres en Roma.

Born in Toulouse in 1960, but since 1970 living with his parents in Rome.

The pronoun “his” is used, but the person we’re talking about could just as well be female. As additional evidence that Google Translate doesn’t use context I will now ask it to translate the following two sentences together:

Julia es una ilustradora francesa. Nació en Tolosa en 1960, pero desde 1970 vive con sus padres en Roma.

Google Translate provides the following translation:

Julia is a French illustrator. Born in Toulouse in 1960, but since 1970 living with his parents in Rome.

Google Translate still uses the word his, yet to any human translator it is blatantly obvious, thanks to the context of the first sentence, that the correct pronoun is her.


Did the Queen have a sex change? Automatic translation of speech

There have been many articles recently, like this one, about advances in the automated translation of speech, and I’ve even read stories about armies using them. I find the latter news very worrying.

Automated translation of speech basically combines two previously existing technologies: speech recognition and machine translation. The problems with the latter are well publicised, and despite the advances made, the problems remain. Google’s corpus-based translations mean that sentences tend to be more coherent nowadays, but a coherent sentence can also be an incorrect translation.

Voice recognition has come on leaps and bounds recently. I use it myself when translating. But as every user of such technology knows, you have to train it to your voice, and even then it makes mistakes that you have to correct. The article from The Times I’ve provided a link to discusses the problem of understanding “high-speed Glaswegian slang”. Current technology would no doubt be absolutely useless at understanding this. But what about more standard forms of English?

I decided to test how Google’s new speech-recognition tool would cope with the Queen’s English — literally the Queen’s English — a speech made by Queen Elizabeth II to parliament in 2009. As I expected, because the tool is not trained to the individual’s voice, the results are pretty awful. To see the video, click on this link. Pause the video, move your mouse over the “CC” button at the bottom of the video, then click on “Transcribe Audio” (don’t click on “English”, as that just gives you captions provided by a human, rather than the automated transcription), click on OK, and the video begins. The Queen tells us how she “was a man that’s in the house of common” [sic].

We can, if we wish, have these captions translated into another language. Just go to the “CC” box and click on “Translate Captions”, then choose your language. But the machine translation will only translate what it’s asked to translate, so we are still likely to get told that the Queen is a man. The translations into the three other languages I work with begin like this:

Catalan: “Jo era un home que està a la Cambra dels Comuns”
Spanish: “Yo era un hombre que está en la Cámara de los Comunes”
French: “J’étais un homme qui est dans la Chambre des communes”

As you can see, there is a very high risk of misunderstanding when using this technology. If the army wants to communicate with people in other languages, I’m afraid they’re just going to have to hire trained interpreters.