JamSpell icon indicating copy to clipboard operation
JamSpell copied to clipboard

Confidence level of candidates

Open subhash-velou opened this issue 5 years ago • 10 comments

I would like to know if there is a way to access confidence level/score for each candidate. For example, in the output below, can we know that the model is 90% confident it's "table", 4% confident its "tale" etc.? { "results": [ { "candidates": [ "table", "tale", "tacle", "tadle", "ladle", "tadre" ], "len": 5, "pos_from": 0 } ] }

I'm having a requirement where I need to apply the fix with top candidate only if the confidence level is above 90%. Would like to understand if you already have this facility or any plans to implement in future.

subhash-velou avatar Sep 12 '18 07:09 subhash-velou

hey. Any luck with this? I exactly need this as sometimes the model makes mistake on task specific texts. Is this going to be implemented or is already implemented?

hejazizo avatar Mar 27 '19 05:03 hejazizo

Anybody here?!!!

hejazizo avatar Mar 28 '19 04:03 hejazizo

i've created a mod that can output JSON with scores assigned to each candidate. Can't open a pull request here to push it though.

jackneil avatar Jul 17 '19 20:07 jackneil

why not? will be glad to accept it

bakwc avatar Jul 17 '19 20:07 bakwc

sorry i was trying to create a pull request on master and it was greyed out. need to branch first?

jackneil avatar Jul 17 '19 20:07 jackneil

yep

bakwc avatar Jul 17 '19 20:07 bakwc

ok i just branched locally to confidenceIntervals but when trying to publish the branch is says permission denied. using vscode.

jackneil avatar Jul 17 '19 20:07 jackneil

you need to publish it to local repository and then create pull request

bakwc avatar Jul 17 '19 21:07 bakwc

@jackneil, how is it going with confidenceIntervals feature? Could you create pull request? Do you need any help?

rprilepskiy avatar Jan 27 '20 13:01 rprilepskiy

Yes we got it implemented and functional. I'll see if the dev on that project can get it pulled and merged. Best

-jack

Jack Neil CEO / Hank AI, Inc. [email protected] (w) +1.828.490.1203 (m) +1.803.466.7551

Sent via Superhuman ( https://sprh.mn/[email protected] )

On Mon, Jan 27, 2020 at 8:40 AM, Roman Prilepskiy < [email protected] > wrote:

@ jackneil ( https://github.com/jackneil ) , how is it going with confidenceIntervals feature? Could you create pull request? Do you need any help?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub ( https://github.com/bakwc/JamSpell/issues/53?email_source=notifications&email_token=AGFRM5UBXSCKM5LZJWYYGILQ73P3NA5CNFSM4FUTGMO2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEJ7QTTA#issuecomment-578750924 ) , or unsubscribe ( https://github.com/notifications/unsubscribe-auth/AGFRM5XWDQJSDGNGYC5IOFLQ73P3NANCNFSM4FUTGMOQ ).

jackneil avatar Jan 27 '20 21:01 jackneil