<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Tahoma
}
--></style>
</head>
<body class='hmmessage'>
Hi,<div>I'm still experimenting with class-based (actually POS) LMs. I use my own 61 classes/PoS. I built a class LM which works fine for decoding. But I also want to compute the perplexity. If I built a mapping file like mentioned in the classes-format manual page (with probabilities=1) I get a ppl of 8.</div><div>So I computed the probabilities for mapping class x to word j as followed:</div><div><br></div><div># word j in class x</div><div>---------------------------</div><div>#occurences of class x</div><div><br></div><div>Now I get a ppl of ~1300. This seems a bit high!?</div><div><br></div><div>I have a total of 20k mappings with a vocab of 12k! The LM is an interpolation of a pure 3g class LM and a 3g word LM. The word LM has usually a ppl of ~500. The ASR Error rate of the word based and interpolated are similar though.</div><div><br></div><div>Can you help me?</div><div>Thanks,</div><div>Fabian</div> </body>
</html>