<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">Ananda,<br>
<br>
the easiest way to have the toolkit compute your bigram and
trigram probabilities once you have the model trained is:<br>
<br>
ngram -lm /home/ananda/Desktop/work/anandamodeling -debug 2
-counts NGRAMS<br>
<br>
where NGRAMS is a file you prepare that lists all the bigrams and
trigrams you need, followed by a "1".<br>
For example:<br>
<br>
i i 1<br>
i want 1<br>
i to 1<br>
want want 1<br>
to to 1<br>
etc.<br>
<br>
Andreas<br>
<br>
<br>
On 8/16/2012 9:14 PM, Ananda K.C. wrote:<br>
</div>
<blockquote
cite="mid:CA+VC5DZCPxaQ6voo1H0KK6RdLD7E-B28Pus3+KrPOiLOrEc3PQ@mail.gmail.com"
type="cite">
<div class="gmail_quote">Dear all,<br>
<br>
I am doing dissertation of my Master's degree in computer
science.I<br>
want to calculate the bigram and trigram probability table as in
attachment,from back off N-gram language models in ARPA format.<br>
<br>
Also when i use this command "ngram-count -order 3 -read
/home/ananda/Desktop/work/countoutput.txt -vocab<br>
/home/ananda/Desktop/work/corpusvocab.txt -lm
/home/ananda/Desktop/work/anandamodeling",which discounting is
use for backoff smothing.<br>
<br>
I am new in the language modeling and thanks in advance.<br>
<br>
<br>
Regards,<br>
Ananda K.C.
</div>
<br>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
SRILM-User site list
<a class="moz-txt-link-abbreviated" href="mailto:SRILM-User@speech.sri.com">SRILM-User@speech.sri.com</a>
<a class="moz-txt-link-freetext" href="http://www.speech.sri.com/mailman/listinfo/srilm-user">http://www.speech.sri.com/mailman/listinfo/srilm-user</a></pre>
</blockquote>
<br>
</body>
</html>