Machine translation and a great many funny examples - When can we expect better results for the automatic translation of text from one language (e.g. English) into an other?
Machine translation, sometimes referred to by the acronym MT, is a sub-field of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to another. At its basic level, MT performs simple substitution of words in one natural language for words in another. Using corpus techniques, more complex translations may be attempted, allowing for better handling of differences in linguistic typology, phrase recognition, and translation of idioms, as well as the isolation of anomalies.
Current machine translation software often allows for customisation by domain or profession (such as weather reports) – improving output by limiting the scope of allowable substitutions. This technique is particularly effective in domains where formal or formulaic language is used. It follows then that machine translation of government and legal documents more readily produces usable output than conversation or less standardised text.
Improved output quality can also be achieved by human intervention: for example, some systems are able to translate more accurately if the user has unambiguously identified which words in the text are names. With the assistance of these techniques, MT has proven useful as a tool to assist human translators, and in some cases can even produce output that can be used “as is”. However, current systems are unable to produce output of the same quality as a human translator, particularly where the text to be translated uses casual language.
Would you like to share some funny examples when translating a foreign language text (snippet) into English?
Here’s my example:
In the transition is apparent that a married woman speaks. The type characterized this as old-fashioned husband. It is probably a ceremony in which the husband probably too much alcoholic punch drunk. Moreover, it is so nearsighted that without glasses, he did not see what is happening around him.
Observing members:
0
Composing members:
0
9 Answers
I’m going to contribute to an answer for the question in your title line. Google and Facebook both have “crowdsourced” translations going on, that is to say, they allow humans to translate small components of the site. Once you have a certain number of people saying “word” means “other word” in other language, and combined with any actual proofing, this is a rather accurate and low cost way of automated translations.
Of course, with each submission, data is created. Eventually, the Googlebot will be able to preemptively translate a page, or take a good stab at it, and let that be corrected by native speakers, so that the next time it learns from its mistakes… I think this type of collective and predictive intelligence will be seen much more often in the future across all sorts of fields.
“The astronauts saw Philadelphia on the way to the moon…”
A machine will NEVER know who was on the way to the moon, the astronauts or Philadelphia ;)
Don’t know how true the story is, but there was supposedly an attempt to create a program that would translate a sentence from English to Russian then back to English again
Original text: the spirit is willing but the flesh is weak.
Came back translated as: the vodka is good but the meat is rotten.
LOL
I like the famous Pepsi one – “Pepsi enlivening a new generation” was translated in Taiwan as “Pepsi brings your ancestors back form the dead!”
Mt is moving forward a lot in reality – there is the recent announcements from both Google and Microsoft that they are facilitating web page translation (http://localization2dot0.lionbridge.com/2009/03/25/fight-night-mt-versus-mt/) and an initiative called TAUS (Translation Automation User Society) that are trying to push the technology as far as possible.
These are all part of Localization 2.0 – I am covering it on my blog – take a look if you are interested…. http://localization2dot0.lionbridge.com
@nicmcmahon – I didn’t know about the Pepsi example. Great! Thanks for sharing this.
@TaoSan
To say a machine will “NEVER” know which one is right I think is too definitive. There are many ways of having a machine know that Philly was not on the way to the moon. As someone who makes a living interpreting into and out of a language, it pains me to say that I do think there will be a time when my job will become obsolete. Luckily the language I work in is a greater challenge for machines, but I think eventually we will be able to map out a language into a way that a machine will understand it as well as us. We have to worry about a time when they know it better than us. When that happens RUN!
Answer this question
This question is in the General Section. Responses must be helpful and on-topic.