Language Log

Smut Clyde at Riddled continues to generate Google Translate poetry:

Adrienne LaFrance, "What an AI's Non-Human Language Actually Looks Like", The Atlantic 6/20/2017:

Something unexpected happened recently at the Facebook Artificial Intelligence Research lab. Researchers who had been training bots to negotiate with one another realized that the bots, left to their own devices, started communicating in a non-human language.  […]

At Riddled, sometime LLOG commenter Smut Clyde has posted an impressive series of Goofle Translate experiments. You can read them at the links below — I've added locally-stored images, based on previous experience with bit rot as well as recent advice from James Angleton.

"Mayor Snorkum will lay the cake" [Snorkum1]
"Reveal to me the unknown tongue": [UnknownTongue1, UnknownTongue2, UnknownTongue3, UnknownTongue4, UnknownTongue5]
"Go home, Google Translate. You are drunk.": [Lovecraft1, Lovecraft2, Lovecraft3]

One more piece of Google Translate poetry, contributed by Mackenzie Morris:

In a series of recent posts we've explored the fun side of recursive weighted sums and point nonlinearities as a translation algorithm: "What a tangled web they weave", "A long short-term memory of Gertrude Stein", "Electric sheep", "The sphere of the sphere is the sphere of the sphere". But the featured translations have all involved inputs of characters in kana, hangul, Thai script, and other non-Latin alphabets, and it's natural to wonder whether this is an essential part of the game.

No — here are various repetitions of "è ", "îî ", and "îè "  translated from Greek:

In a comment on "Electric Sheep", Tim wrote:

Just want to share a little Google Translate poetry resulting from drumming my fingers on the keyboard while set to Thai:

There are six sparks in the sky, each with six spheres. The sphere of the sphere is the sphere of the sphere.

A couple of recent LLOG posts ("What a tangled web they weave", "A long short-term memory of Gertrude Stein") have illustrated the strange and amusing results that Google's current machine translation system can produce when fed variable numbers of repetitions of meaningless letter sequences in non-Latin orthographic systems. [Update: And see posts in the elephant semifics category for many other examples.] Geoff Pullum has urged me to explain how and why this sort of thing happens:

I think Language Log readers deserve a more careful account, preferably from your pen, of how this sort of craziness can arise from deep neural-net machine translation systems. […]

Ordinary people imagine (wrongly) that Google Translate is approximating the process we call translation. They think that the errors it makes are comparable to a human translator getting the wrong word (or the wrong sense) from a dictionary, or mistaking one syntactic construction for another, or missing an idiom, and thus making a well-intentioned but erroneous translation. The phenomena you have discussed reveal that something wildly, disastrously different is going on.  

Something nonlinear: 18 consecutive repetitions of a two-character Thai sequence produce "This is how it is supposed to be", and so do 19, 20, 21, 22, 23, and 24, and then 25 repetitions produces something different, and 26 something different again, and so on. What will come out in response to a given input seems informally to be unpredictable (and I'll bet it is recursively unsolvable, too; it's highly reminiscent of Emil Post's famous tag system where 0..X is replaced by X00 and 1..X is replaced by X1101, iteratively).

Type "La plume de ma tante est sur la table" into Google Translate and ask for an English translation, and you get something that might incline you, if asked whether you would agree to ride in a self-driving car programmed by the same people, to say yes. But look at the weird shit that comes from inputting Asian language repeated syllable sequences and you not only wouldn't get in the car, you wouldn't want to be in a parking lot where it was driving around on a test run. It's the difference between what might look like a technology nearly ready for prime time and the chaotic behavior of an engineering abortion that should strike fear into the hearts of any rational human.  

Language Log needs at least a sketch of a proper serious account of what's going on here.

A sketch is all that I have time for today, but here goes…

As just observed ("What a tangled web they weave"), successive repetitions of short sequences of Japanese, Korean, Thai (and perhaps other types of) characters cause Google's Neural Machine Translation system to generate surprisingly varied and poetic English equivalents.

Thus if we repeat 1 through 25 times the two-character Thai sequence ไๅ

|ไ| 0x0E44 "THAI CHARACTER SARA AI MAIMALAI"
|ๅ| 0x0E45 "THAI CHARACTER LAKKHANGYAO"

the system, "a deep LSTM network with 8 encoder and 8 decoder layers using attention, residual connections, and trans-temporal chthonic affinity", establishes a pretty solid spiritual connection with Gertrude Stein:

…when neural nets are recursive:

This is weird, and even slightly creepy — paste a list of countries like

Costa Rica, Argentina, Belgium, Bulgaria, Canada, Chile, Colombia, Dominican Republic, Ecuador, El Salvador, Ethiopia, France, Germany, England, Guatemala, Honduras, Italy, Israel, Mexico, New Zealand, Nicaragua, Peru, Puerto Rico, Scotland, Switzerland, Spain, Sweden, Uruguay, Venezuela, USA

into Google Translate English-to-Spanish, and a parallel-universe list emerges: