News for hackers. Stuff that matters.
Re:Finnish breaks natural language processors by hpaavola on Friday March 01, 2019 @04:34AM (#19279068)
Finn here. There are countless memes about oddities of our language. The one I like the most is "kuusi palaa". It can mean;

   the spruce is on fire
   the spruce returns
   the number six is on fire
   the number six returns
   six of them are on fire
   six of them return
   your moon is on fire
   your moon returns
   six pieces
Good luck for all implementing NLP :)
Re:Finnish breaks natural language processors by stevekemp on Friday March 01, 2019 @04:59AM (#19279187)
I like the "dog example" too, which highlights the different forms/cases:

https://linustechtips.com/main/topic/72936-english-swedish-g...

I'm a recent immigrant to Finland, and while the regular grammar makes some things simple, the cases and suffixes are enough to drive me crazy! The simple things are easy to handle if you're reading a textbook, but remembering them in real-time when speaking is very hard.

Re:Finnish breaks natural language processors by BerislavLopac on Friday March 01, 2019 @05:08AM (#19279224)
No wonder Tolkien used it as a basis for Elvish.
Re:Finnish breaks natural language processors by arka2147483647 on Friday March 01, 2019 @08:36AM (#19280430)
This is a specificially constructed corner case, not a general finnish thing:

- kuu = moon

- kuusi = spruce

- palaa = returns

- pala = piece

From those you can see how one can intrepent the compound word (with or without suffix) however you wish.

Eg:

- kuu+si = your moon (where 'si' is the suffix which means 'your')

- pala+a = pieces (where 'a' suffix is the plural)

Re:Finnish breaks natural language processors by kbouck on Friday March 01, 2019 @02:28PM (#19284409)
also:

- kuusi = six

Re:Finnish breaks natural language processors by fakghy on Saturday March 02, 2019 @08:24AM (#19289138)
- palaa = burning
Re:Finnish breaks natural language processors by Whatitat90 on Friday March 01, 2019 @04:54AM (#19279163)
I wonder what oddities lie in Linus Torvalds' "perkeleen vittupää" (https://lkml.org/lkml/2013/7/13/132).
Re:Finnish breaks natural language processors by jacobush on Friday March 01, 2019 @05:23AM (#19279297)
I'm afraid it very unambiguously just means fucking cunts.
Re:Finnish breaks natural language processors by Ezku on Friday March 01, 2019 @05:52AM (#19279424)
In singular genetive and nominative cases no less, so, absolutely no grammatical fancy going on there.
Re:Finnish breaks natural language processors by josmala on Friday March 01, 2019 @07:37AM (#19279974)
Its literal translation is.

Satan's cunt-head

Re:Finnish breaks natural language processors by uasm on Friday March 01, 2019 @07:14AM (#19279804)
> "kuusi palaa"

Can we get a bit more detail here? Are those variations on pronunciation? How does a native Finn able to infer the correct meaning?

Re:Finnish breaks natural language processors by emilfihlman on Friday March 01, 2019 @08:10AM (#19280192)
Finnish is pronounced extremely regularly. The way it's written is the way it's pronounced (in almost all cases).
Re:Finnish breaks natural language processors by gorbachev on Friday March 01, 2019 @07:22AM (#19279870)
No, there is no variation on pronunciation. They sound exactly the same when spoken.

The only way to infer what's meant is from context.

Re:Finnish breaks natural language processors by simonh on Friday March 01, 2019 @09:08AM (#19280695)
My favourite homophone example is a 92 character poem in Chinese[0], where every syllable is a slight variation on Shi.

[0]https://en.wikipedia.org/wiki/Lion-Eating_Poet_in_the_Stone_...

Interestingly when I showed the actual text to my wife, who is Chinese, she didn't understand what was funny about it until I asked her to read it to me, when she burst out laughing. That's when I found out she doesn't sub-vocalise, where I do all the time.

Re:Finnish breaks natural language processors by apendleton on Friday March 01, 2019 @11:13AM (#19282026)
These aren't really homophones though, right? Because they differ in tone?
Re:Finnish breaks natural language processors by yorwba on Friday March 01, 2019 @11:30AM (#19282274)
There are only 4 different tones, so by the pigeonhole principle there must be lots of homophones.

On the other hand, most of the characters used to be pronounced differently when they were still commonly used as individual words, so the poem only works because it mixes modern pronunciation with classical grammar.

Re:Finnish breaks natural language processors by appsonify on Friday March 01, 2019 @11:50AM (#19282559)