zlacker

[parent] [thread] 4 comments
1. petarg+(OP)[view] [source] 2020-05-13 19:11:39
This is pretty cool but I am getting some strange results sometimes:

https://imgur.com/a/rv0wHN1

replies(1): >>turtle+N
2. turtle+N[view] [source] 2020-05-13 19:15:29
>>petarg+(OP)
That's not ideal and probably picking up some of the original training set from GPT-2 (this model is bolted on top of it)! How about DUOLINGOLOGY instead https://bit.ly/3fPGP8q

I'm using a blacklist to reject "real" words but it's surprisingly hard to build for rare words. I'm up to ~600K items after parsing Wikipedia tokens and it still doesn't capture everything.

replies(3): >>petarg+c1 >>kube-s+O4 >>AdamTR+J5
◧◩
3. petarg+c1[view] [source] [discussion] 2020-05-13 19:17:55
>>turtle+N
That's understandable! Another one I got was "whitepaper".

In any case, it's all pretty impressive! Defintely something one can use for creative writing or fantasy world building.

◧◩
4. kube-s+O4[view] [source] [discussion] 2020-05-13 19:37:46
>>turtle+N
It seems to make compound words just like humans do

gigafactory

nonplayable

waterboy

pepperjack

unreimbursed

interop

nonalloyed

backdoored

◧◩
5. AdamTR+J5[view] [source] [discussion] 2020-05-13 19:41:48
>>turtle+N

  airpods
  air·pods
  a large pair of wings and wings of a bird or other flying 
  animal, typically used as a guide for a figure skater and 
  paraglider
  "a pair of airpods"
[go to top]