Hi all,
In my project I need language model to calculate the probability of each
sentence, I have to use kenlm https://kheafield.com/code/kenlm/ but for
some sentences give me wrong probability when the sentences have words not
analysis like this:
Курчатов – Шар темір жолы салынды, ал оның жа
El 2018-08-15 19:34, mansur escribió:
Fran, could you show me how exactly I should use them? A couple of
examples, please :)
Something like:
nothing:nowt PRON ; ! "" ! Dial/North
receive:recieve V ; ! "" ! Err/Orth
Fran
Fran, could you show me how exactly I should use them? A couple of
examples, please :)
Am Mi., 15. Aug. 2018 um 17:49 Uhr schrieb Francis Tyers :
>
> El 2018-08-15 15:06, mansur escribió:
> > Hello!
> >
> > We have quite many words in our Apertium's Tatar dictionary, including
> > dialectological,
El 2018-08-15 15:06, mansur escribió:
Hello!
We have quite many words in our Apertium's Tatar dictionary, including
dialectological, spoken and historical ones. But for our spellchecker
we must use literary words only, that's why spellchecker's quality
currently is quite low. So I want to mark s
Hello!
We have quite many words in our Apertium's Tatar dictionary, including
dialectological, spoken and historical ones. But for our spellchecker
we must use literary words only, that's why spellchecker's quality
currently is quite low. So I want to mark somehow (!SPELL ???)
literary words in th