.\" $Id: pfsg-format.5,v 1.3 2007/12/19 22:08:05 stolcke Exp $
.TH pfsg-format 5 "$Date: 2007/12/19 22:08:05 $" "SRILM File Formats"
.SH NAME
pfsg-format \- File format for Decipher(TM) probabilistic finite-state grammars
.SH SYNOPSIS
.nf
\fBname\fP \fIname\fP
\fBnodes\fP \fIN\fP \fIw1\fP ... \fIwN\fP
\fBinitial\fP \fIi\fP
\fBfinal\fP \fIf\fP
\fBtransitions\fP \fIT\fP
\fIn1\fP \fIn2\fP \fIp\fP
\&...
.fi
.SH DESCRIPTION
Probabilistic finite-state grammars (PFSGs) are a form of finite-state
automaton or transducer used by the SRI Decipher(TM) recognizer.
PFSGs emit words (outputs) at the nodes, not on the arcs.
Certain types of language models manipulated by SRILM can be 
translated into PFSGs for direct use in the recognizer.
.PP
Since it is usually fairly easy to convert between different
finite-state network representations, PFSGs can serve as 
an intermediate format for the generation of other finite-state formats.
For example, PFSGs can be converted to the AT&T
.BR fsm (5)
format.
.PP
Each PFSGs is given a
.IR name .
The name is significant if PFSGs are to be composed, in which case the
.I name 
specifies the category it expands.
.PP
The
.B nodes
line gives the number of nodes in the state graph, followed by the
word strings associated with each node.
If the node represents a category expanded by another PFSG, then the
name string of that PFSG is given here.
The token
.B NULL
is special and designates the corresponding node as non-emitting.
It is conventional to use lowercase strings for words, and uppercase
for categories and PFSG names (``NULL'' must be avoided, of course).
.PP
The
.B initial
and
.B final
lines specify the start and end states of the grammar, respectively.
Nodes are numbered starting at zero.
.PP
The 
.B transitions
line gives the number of arcs (transitions) between states.
It is followed by as many lines, each specifying one transition
by its 
originating state
.IR n1 ,
its target state
.IR n2 ,
and the transition cost
.IR p .
The transition cost is usually interpreted as 10000.5 times the natural
logarithm of a probability, and should be normalized and scaled
accordingly.
.SH "SEE ALSO"
pfsg-scripts(1), fsm(1).
.SH BUGS
File formats are a matter of taste ...
.br
There is no way to specify words with embedded whitespace.
.SH AUTHOR
PFSGs were developed as part of SRI's Decipher(TM) recognition system.
Manual page written by 
Andreas Stolcke <stolcke@speech.sri.com>.
.br
Copyright 1999, 2004 SRI International