<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=gb2312">
<META content="MSHTML 6.00.2900.3562" name=GENERATOR>
<STYLE>BLOCKQUOTE {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px; MARGIN-LEFT: 2em
}
OL {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px
}
UL {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px
}
</STYLE>
</HEAD>
<BODY style="FONT-SIZE: 10pt; FONT-FAMILY: verdana">
<DIV><FONT face=Verdana size=2>Dear SRILM users,</FONT></DIV>
<DIV> I wanted to get a BiGram from the word pair counts file,</DIV>
<DIV>so I took it as :</DIV>
<DIV> ngram-count -read CountFile -lm -BiGrams -order 2</DIV>
<DIV>But several minutes later, it was killed.</DIV>
<DIV> </DIV>
<DIV>I suspect my CountFile is too large(3.5GB) ,and my
memmoy is 2.0GB.</DIV>
<DIV>so if the CountFiles is read in memory, it will be overflow.</DIV>
<DIV> </DIV>
<DIV>So my question is ,</DIV>
<DIV>1:Does the SRILM reads the whole CountFile in memory?</DIV>
<DIV> or read some lines and train some BiGrams ,them again and
again?</DIV>
<DIV> </DIV>
<DIV>2:How can I do to get the BiGram with this large CountFile?</DIV>
<DIV> </DIV>
<DIV>Thanks,</DIV>
<DIV> Wang</DIV>
<DIV><FONT face=Verdana color=#c0c0c0 size=2></FONT> </DIV><FONT
face=Verdana size=2>
<DIV> </DIV></FONT></BODY></HTML>