Re:Unsupervised Machine Translation Using Monolingual Corpor...
by benkuhn on Thursday November 02, 2017 @02:10PM
(#15612758)
I think you missed something.
Previously, machine translation required being trained on a bilingual corpus, that is, a corpus of the same set of sentences in eg English and French. These corpora are pretty hard to come by and expensive to produce.
The paper describes a technique to use two monolingual corpora instead, i.e. one set of sentences in English and a different set of sentences in French. That's way easier to find.
It's far from just a definitional trick.
Re:Unsupervised Machine Translation Using Monolingual Corpor...
by JPLeRouzic on Friday November 03, 2017 @05:43AM
(#15617845)
>> These corpora are pretty hard to come by and expensive to produce.
Actually there are lot of texts translated by qualified translators in several languages, for political reasons: EU's commission websites, perhaps some other countries official websites.
You can have a look at Linguee [0] which uses this to provide translation suggestions:
An analogy is an experiment where a scientist says "I can prove these two people have ESP and can pick the same #". He sits them in two separate rooms and has her first pick a number. He goes to the second room and has him pick a number. 17? No higher. 24? No higher. 52? No lower. 43? Yes exactly!!
"See, these two people both came up with the same number without any communication with each other. ESP!"
If they want to show this language learning is powerful, demonstrate that once trained it can now be applied to a third language without any new "adversarial feedback".
Or it reminds me of the fake "we can communicate faster than light via quantum entanglement" claims. But then the caveat comes that they can only figure out what the value of the bit of info they communicated was causally.