Slashdot Mirror
AI Goes Bilingual -- Without a Dictionary (sciencemag.org)
sciencehabit shares a report from Science Magazine: Automatic language translation has come a long way, thanks to neural networks -- computer algorithms that take inspiration from the human brain. But training such networks requires an enormous amount of data: millions of sentence-by-sentence translations to demonstrate how a human would do it. Now, two new papers show that neural networks can learn to translate with no parallel texts -- a surprising advance that could make documents in many languages more accessible.
The two new papers, both of which have been submitted to next year's International Conference on Learning Representations but have not been peer reviewed, focus on another method: unsupervised machine learning. To start, each constructs bilingual dictionaries without the aid of a human teacher telling them when their guesses are right. That's possible because languages have strong similarities in the ways words cluster around one another. The words for table and chair, for example, are frequently used together in all languages. So if a computer maps out these co-occurrences like a giant road atlas with words for cities, the maps for different languages will resemble each other, just with different names. A computer can then figure out the best way to overlay one atlas on another. Voila! You have a bilingual dictionary. The studies -- "Unsupervised Machine Translation Using Monolingual Corpora Only" and "Unsupervised Neural Machine Translation" -- were both submitted to the e-print archive arXiv.org.
The two new papers, both of which have been submitted to next year's International Conference on Learning Representations but have not been peer reviewed, focus on another method: unsupervised machine learning. To start, each constructs bilingual dictionaries without the aid of a human teacher telling them when their guesses are right. That's possible because languages have strong similarities in the ways words cluster around one another. The words for table and chair, for example, are frequently used together in all languages. So if a computer maps out these co-occurrences like a giant road atlas with words for cities, the maps for different languages will resemble each other, just with different names. A computer can then figure out the best way to overlay one atlas on another. Voila! You have a bilingual dictionary. The studies -- "Unsupervised Machine Translation Using Monolingual Corpora Only" and "Unsupervised Neural Machine Translation" -- were both submitted to the e-print archive arXiv.org.
In order to go "bilingual", it would have to be able to understand one language first. However understanding natural language is so far beyond the demented automation ("weak AI") available today, it is not even funny anymore. May as well claim a squirrel is a "gourmet chef", because it can bury nuts, i.e. "process food". Whether actual intelligence is going to be available on machines, ever, is at this time completely unknown, because nobody knows what it is. It is pretty clear though that the only natural computing hardware known (the human brain) is not powerful enough to create the intelligence observable at the interface of the smartest instances, at least if any known computing paradigm is assumed to be how it works. So either a completely computing paradigm is needed (and no, "neural" nets will not cut it and they are really old), or the problem is even more complicated.
The real problem here is that most people are not smart enough to recognize a moron if the moron is dressed up prettily and spews pseudo-profound bullshit. Just look at who people vote for.
Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
That would be fine. The number of times I wanted a machine translated story in the past... I dunno, ever. 0. The number of times I wanted a technical paper, or instructions or tech specs are significant. Or even news. Storytelling, jokes and wordplay are the least interesting thing to translate, because there are people who actually already do that.
Your ad here. Ask me how!
These are very cool advances, but they don't solve the major problem of machine learning (ML): Having lots of data.
While these approaches don't need bilingual corpora, they still need big monolingual corpora. Very few languages have those, and those that do usually also have bilingual corpora to one or more of the major world languages.
This does lower the barrier to entry significantly for those doing ML machine translation. But, if one took the resources spent on gathering and curating corpora and instead invested in rule-based systems, you could get much further in less time.
The assumption, that the world is the same, and languages are attached to it, lies at the bottom of the idea of this learning strategy. The example given - of 'table and chairs' demonstrates this. Most of these ideas belong to a 19th century eurocentric understanding of the world we live in. Modern neuroscience and other work points to the fact that the world we perceive is very much dominated by the language we use, and not the other way around.
Concrete Example: For a large portion of the 19th-20th Century many Greeks measured distance in cigarettes - how many cigarettes I will smoke while travelling from one place to another. There is no cognate in English for this. Not only that, but the language usage indicates a specific timespan as well as cultural differences.
"Idiom!" I hear you say. Consider cultures where there are many more tables than there are chairs - such as in Asia where most people sit on the floor or on cushions.
"But there are some universals - we can still use those!" - generally, there are no universals, or so few that they are not worth talking about. Talk to an anthropologist about it. Not even the concept of 'mother' is a universal.
This comment was written with the intention to opt out of advertising.