<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML>
<HEAD>
<TITLE>class EST_SCFG_traintest</TITLE>
<META NAME="GENERATOR" CONTENT="DOC++ 3.4.6">
</HEAD>
<body bgcolor="#ffffff" link="#0000ff"
vlink="#dd0000" text="#000088" alink="9000ff">
<A HREF = "http://www.cstr.ed.ac.uk/">
<IMG align=left BORDER=0 SRC = "cstr.gif"></A>
<A HREF="http://www.cstr.ed.ac.uk/projects/speech_tools.html">
<IMG BORDER=0 ALIGN=right SRC="est.jpg" width=150 height=93></A>
<br>
<br clear=left>
<p align=right>
In file ../include/EST_SCFG.h:<TABLE BORDER=0><TR>
<TD VALIGN=TOP><H2>class <A HREF="#DOC.DOCU">EST_SCFG_traintest</A></H2></TD></H2></TD></TR></TABLE>
<BLOCKQUOTE>A class used to train (and test) SCFGs is an extention of <!1><A HREF="EST_SCFG.html">EST_SCFG</A>.</BLOCKQUOTE>
<HR>
<H2>Inheritance:</H2>
<APPLET CODE="ClassGraph.class" WIDTH=600 HEIGHT=65>
<param name=classes value="CEST_SCFG,MEST_SCFG.html,CEST_SCFG_traintest,MEST_SCFG_traintest.html">
<param name=before value="M,M">
<param name=after value="Md_,M">
<param name=indent value="0,1">
<param name=arrowdir value="down">
</APPLET>
<HR>
<DL>
<P><TABLE>
<DT><H3>Public Methods</H3><DD><TR>
<TD VALIGN=TOP><A HREF="#DOC.106.17"><IMG ALT="[more]" BORDER=0 SRC=icon1.gif></A>void </TD><TD><B>test_corpus</B> ()<BR>
<I>Test the current grammar against the current corpus print summary.</I>
</TD></TR><TR>
<TD VALIGN=TOP><A HREF="#DOC.106.18"><IMG ALT="[more]" BORDER=0 SRC=icon1.gif></A>void </TD><TD><B>test_crossbrackets</B> ()<BR>
<I>Test the current grammar against the current corpus.</I>
</TD></TR><TR>
<TD VALIGN=TOP><A HREF="#DOC.106.19"><IMG ALT="[more]" BORDER=0 SRC=icon1.gif></A>void </TD><TD><B>load_corpus</B> (const <!1><A HREF="EST_String.html">EST_String</A> &<!1><A HREF="EST_TokenStream.html#DOC.10.7.9">filename</A>)<BR>
<I>Load a corpus from the given file.</I>
</TD></TR><TR>
<TD VALIGN=TOP><A HREF="#DOC.106.20"><IMG ALT="[more]" BORDER=0 SRC=icon1.gif></A>void </TD><TD><B>train_inout</B> (int passes, int startpass, int checkpoint, int spread, const <!1><A HREF="EST_String.html">EST_String</A> &outfile)<BR>
<I>Train a grammar using the loaded corpus.</I>
</TD></TR></TABLE></P>
</DL>
<HR><H3>Inherited from <A HREF="EST_SCFG.html">EST_SCFG</A>:</H3>
<DL>
<P><DL>
<DT><H3>Public Methods</H3><DD><DT>
<P> <B>Constructor and initialisation functions </B>
<P><DL>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif> <B><A HREF="#DOC.105.1.1">EST_SCFG</A></B>(LISP <!1><A HREF="EST_SCFG.html#DOC.105.2.3">rules</A>)
<DD><I>Initialize from a set of rules</I>
</DL></P>
<DT>
<P> <B>utility functions </B>
<P><DL>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>void <B><A HREF="#DOC.105.2.1">set_rules</A></B>(LISP <!1><A HREF="EST_SCFG.html#DOC.105.2.3">rules</A>)
<DD><I>Set (or reset) rules from external source after construction</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>LISP <B><A HREF="#DOC.105.2.2">get_rules</A></B>()
<DD><I>Return rules as LISP list</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>SCFGRuleList <B><A HREF="#DOC.105.2.3">rules</A></B>
<DD><I>The rules themselves</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>void <B><A HREF="#DOC.105.2.4">find_terms_nonterms</A></B>(EST_StrList &nt, EST_StrList &<!1><A HREF="EST_Wave.html#DOC.81.4.5">t</A>, LISP <!1><A HREF="EST_SCFG.html#DOC.105.2.3">rules</A>)
<DD><I>Find the terminals and nonterminals in the given grammar, adding them to the appropriate given string lists</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif><!1><A HREF="EST_String.html">EST_String</A> <B><A HREF="#DOC.105.2.5">nonterminal</A></B>(int <!1><A HREF="XML_Parser.html#DOC.190.3.9">p</A>) const
<DD><I>Convert nonterminal index to string form</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif><!1><A HREF="EST_String.html">EST_String</A> <B><A HREF="#DOC.105.2.6">terminal</A></B>(int m) const
<DD><I>Convert terminal index to string form</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>int <B><A HREF="#DOC.105.2.7">nonterminal</A></B>(const <!1><A HREF="EST_String.html">EST_String</A> &<!1><A HREF="XML_Parser.html#DOC.190.3.9">p</A>) const
<DD><I>Convert nonterminal string to index</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>int <B><A HREF="#DOC.105.2.8">terminal</A></B>(const <!1><A HREF="EST_String.html">EST_String</A> &m) const
<DD><I>Convert terminal string to index</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>int <B><A HREF="#DOC.105.2.9">num_nonterminals</A></B>() const
<DD><I>Number of nonterminals</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>int <B><A HREF="#DOC.105.2.10">num_terminals</A></B>() const
<DD><I>Number of terminals</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>double <B><A HREF="#DOC.105.2.11">prob_B</A></B>(int <!1><A HREF="XML_Parser.html#DOC.190.3.9">p</A>, int q, int r) const
<DD><I>The rule probability of given binary rule</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>double <B><A HREF="#DOC.105.2.12">prob_U</A></B>(int <!1><A HREF="XML_Parser.html#DOC.190.3.9">p</A>, int m) const
<DD><I>The rule probability of given unary rule</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif>void <B><A HREF="#DOC.105.2.13">set_rule_prob_cache</A></B>()
<DD><I>(re-)set rule probability caches</I>
</DL></P>
<DT>
<P> <B>file i/o functions </B>
<P><DL>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif><!1><A HREF="EST_read_status.html">EST_read_status</A> <B><A HREF="#DOC.105.3.1">load</A></B>(const <!1><A HREF="EST_String.html">EST_String</A> &<!1><A HREF="EST_TokenStream.html#DOC.10.7.9">filename</A>)
<DD><I>Load grammar from named file</I>
<DT>
<IMG ALT="[more]" BORDER=0 SRC=icon1.gif><!1><A HREF="EST_write_status.html">EST_write_status</A> <B><A HREF="#DOC.105.3.2">save</A></B>(const <!1><A HREF="EST_String.html">EST_String</A> &<!1><A HREF="EST_TokenStream.html#DOC.10.7.9">filename</A>)
<DD><I>Save current grammar to named file</I>
</DL></P>
</DL></P>
</DL>
<A NAME="DOC.DOCU"></A>
<HR>
<H2>Documentation</H2>
<BLOCKQUOTE>A class used to train (and test) SCFGs is an extention of
<!1><A HREF="EST_SCFG.html">EST_SCFG</A>.
<P>This offers an implementation of Pereira and Schabes ``Inside-Outside
reestimation from partially bracket corpora.'' ACL 1992.
<P>A SCFG maybe trained from a corpus (optionally) containing brackets
over a series of passes reestimating the grammar probabilities
after each pass. This basically extends the <!1><A HREF="EST_SCFG.html">EST_SCFG</A> class
adding support for a bracket corpus and various indexes for efficient
use of the grammar.</BLOCKQUOTE>
<DL>
<A NAME="test_corpus"></A>
<A NAME="DOC.106.17"></A>
<DT><IMG ALT="o" BORDER=0 SRC=icon2.gif><TT><B>void test_corpus()</B></TT>
<DD>Test the current grammar against the current corpus print summary.
<P>Cross entropy measure only is given.
<DL><DT><DD></DL><P>
<A NAME="test_crossbrackets"></A>
<A NAME="DOC.106.18"></A>
<DT><IMG ALT="o" BORDER=0 SRC=icon2.gif><TT><B>void test_crossbrackets()</B></TT>
<DD>Test the current grammar against the current corpus.
<P>Sumamry includes percentage of cross bracketing accuracy
and percentage of fully correct parses.
<DL><DT><DD></DL><P>
<A NAME="load_corpus"></A>
<A NAME="DOC.106.19"></A>
<DT><IMG ALT="o" BORDER=0 SRC=icon2.gif><TT><B>void load_corpus(const <!1><A HREF="EST_String.html">EST_String</A> &<!1><A HREF="EST_TokenStream.html#DOC.10.7.9">filename</A>)</B></TT>
<DD>Load a corpus from the given file.
<P>Each setence in the corpus should be contained in parentheses.
Additional paranethesis may be used to denote phrasing within
a sentence. The corpus is read using the LISP reader so LISP
conventions shold apply, notable single quotes should appear
within double quotes.
<DL><DT><DD></DL><P>
<A NAME="train_inout"></A>
<A NAME="DOC.106.20"></A>
<DT><IMG ALT="o" BORDER=0 SRC=icon2.gif><TT><B>void train_inout(int passes, int startpass, int checkpoint, int spread, const <!1><A HREF="EST_String.html">EST_String</A> &outfile)</B></TT>
<DD>Train a grammar using the loaded corpus.
<P>
<DL><DT><DT><B>Parameters:</B><DD><B>passes</B> - the number of training passes desired.
<BR><B>startpass</B> - from which pass to <!1><A HREF="EST_Track.html#DOC.71.7.9">start</A> from
<BR><B>checkpoint</B> - <!1><A HREF="EST_SCFG.html#DOC.105.3.2">save</A> the <!1><A HREF="EST_SCFG_Chart.html#DOC.110.1">grammar</A> every <!1><A HREF="EST_SCFG_traintest.html#DOC.106.3">n</A> passes
<BR><B>spread</B> - Percentage of corpus to use on each pass,
this cycles through the corpus on each pass.<BR><DD></DL><P></DL>
<HR><DL><DT><B>This class has no child classes.</B></DL>
<DL><DT><DD></DL><P><P><I><A HREF="index.html">Alphabetic index</A></I> <I><A HREF="HIER.html">HTML hierarchy of classes</A> or <A HREF="HIERjava.html">Java</A></I></P><HR>
<A HREF = "http://www.ed.ac.uk/">
<IMG align=right BORDER=0 SRC = "edcrest.gif"></A>
<P Align=left><I>This page is part of the
<A HREF="http://www.cstr.ed.ac.uk/projects/speech_tools.html">
Edinburgh Speech Tools Library</A> documentation
<br>
Copyright <A HREF="http://www.ed.ac.uk"> University of Edinburgh</A> 1997
<br>
Contact: <A HREF="mailto:speech_toolss@cstr.ed.ac.uk">
speech_tools@cstr.ed.ac.uk </a>
</P>
<br clear=right>
distrib
>
Fedora
>
14
>
x86_64
>
media
>
updates
>
by-pkgid
>
0e54ba0ee564ce6063a5e83aa86060c5
>
files
>
214
