About the generation of similar words
#71
(31-03-2026, 03:36 PM)quimqu wrote: You are not allowed to view links. Register or Login to view.....
To test this, I stopped grouping tokens into “families” (that was too unstable) and instead looked only at direct pairs of similar tokens (Levenshtein = 1). Then I compared their contextual profiles. The result is quite strong: tokens that are formally similar have much more similar contexts than expected. Not slightly more. A lot more.
...

Could you explain what you mean by "context"? Sorry if I missed it.
Reply
#72
Register or login to view the content
[+] 1 user says Thank You to quimqu for this post
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Similar words in the same position bi3mw 11 15,725 28-06-2018, 07:36 AM
Last Post: MarcoP

Forum Jump:


Users browsing this thread: 1 Guest(s)