I read recently that researchers at Google are tackling what they call one of the most difficult challenges in artificial intelligence.
Programming a machine to simply understand language, after all, is a task IBM spent four years and millions of dollars to accomplish with its Watson computer, which competed on Jeopardy last week. Watson understands human speech. But for a computer to understand and translate poetry, there are added problems of length, meter and rhyme.
Most translation software works by searching through a wealth of possible translations, then evaluating what’s most accurate.
Whereas, if you translate poetry, you have to preserve what you want the reader to feel.
Translating a haiku? Preprogram the computer to generate online lines of five, seven and five syllables.
A Shakespeare sonnet in iambic pentameter? The computer can read a pronunciation dictionary. Once it knows where the stress falls in a given word, it can correctly place that word in a metered sentence.
I personally feel translating perspective is more difficult in poetry. Vladimir Nabokov famously claimed it’s impossible for even a human preserve both the meaning and form of a translated poem.
The hardest thing to do is rhyme, because it connects to different places in a sentence, and because two words that rhyme in English may not rhyme in another language. In that case, the best it can do is to cycle through a long list of optional matches to find a rhyme that’s right.
That means, if you’re translating Edgar Allan Poe’s The Raven:
Once upon a midnight dreary, while I pondered weak and teary…
For every close option, the computer also cycles through a choice that’s not even close:
Once upon a midnight dreary, while I pondered weak and orange.
It sure is a work in progress and I am pretty sure Shakespeare would not like this Welsh translation of the title.
mae cynnydd o unrhyw enw arall.