zlacker

[return to "Show HN: This Word Does Not Exist"]
1. petarg+M9[view] [source] 2020-05-13 19:11:39
>>turtle+(OP)
This is pretty cool but I am getting some strange results sometimes:

https://imgur.com/a/rv0wHN1

◧◩
2. turtle+za[view] [source] 2020-05-13 19:15:29
>>petarg+M9
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.

◧◩◪
3. kube-s+Ae[view] [source] 2020-05-13 19:37:46
>>turtle+za
It seems to make compound words just like humans do

gigafactory

nonplayable

waterboy

pepperjack

unreimbursed

interop

nonalloyed

backdoored

[go to top]