Hello Rico,
Thank you so much for your help.
Yes, the model is made from a very small corpus.
I will try to calculate the log probabilities
with other RDLM files made from huge corpora.
Best regards,
Madori
___
Moses-support mailing list
Moses-support
Hello Madori,
your procedure looks alright. The final log probability of the sentence
is the sum of the log probabilities of the label model and the head
model. [although your log probabilities look very high; this is ok if
you only trained a toy model so far].
best wishes,
Rico
On 09/07/16 0
Rico Sennrich writes:
>
>
> Hello Madori,
> the query command is specific to n-gram LMs in the ARPA format (or
> a compiled format of KenLM).
> Here is how you can measure log probabilities with RDLM (or NPLM
> in general):
> 1. extract the n-grams (for NPLM) o
Hello Madori,
the query command is specific to n-gram LMs in the ARPA format (or a
compiled format of KenLM).
Here is how you can measure log probabilities with RDLM (or NPLM in
general):
1. extract the n-grams (for NPLM) or syntactic n-grams (for RDLM) from
the test set, with the same set
Hello,
I'm trying to evaluate fluentness of text based on RDLM,
and I think query command can do that like described in Moses manual Sec.
2.3.4.
The question is how can I use the query command with RDLM ?
RDLM is constructed and separated into two files (head / label mode) in
Moses (in the manual