count_artvec.1

有关自然语言理解理解方面的源码

.\" Process this file with 
.\"    groff -man -Tascii count_artvec.1.

.TH COUNT_ARTVEC 1 "February 2004" "Infomap Project" "Infomap NLP Manual"

.SH NAME
.TP 
count_artvec \- compute article vectors from word vectors and \
tokenized corpus

.SH SYNOPSIS
.B count_artvec
.BR -m " <model_data_dir> "

.SH DESCRIPTION
.B count_artvec


.SH OPTIONS
.TP
.BI -m \ <model_data_dir>
The directory from which input files are read and to which output
files are written.

.\" .SH EXAMPLES

.SH INPUT FILES
These files are read from the model data directory, specified as
an argument to the
.B -mdir
option.

.I numDocs
.RS
A file containing the number of documents in the input corpus.
See
.BR prepare_corpus (1).
.RE

.I dic
.RS
The "dictionary" file listing the word types (terms) from the input
corpus, along with their term and document frequencies.
See 
.BR prepare_corpus (1).
.RE

.I wordlist
.RS
A tokenized form of the corpus, with document boundaries marked.
See
.BR prepare_corpus (1).
.RE

.I wordvec.bin
.RS
A binary representation of the word vectors.  See 
.BR encode_wordvec (1).
.RE

.I model_params.bin
.RS
Reads this file to obtain parameters for the model being built.
See 
.BR prepare_corpus (1).
.RE

.SH OUTPUT FILES
These files are written to the model data directory, specified as
an argument to the
.B -mdir
option.

.I artvec.bin
.RS
A binary representation of the article vectors.  Analogous
to 
.IR wordvec.bin .
.RE

.I art2offset.{dir,pag}
.RS
These two files make up a DBM database.  Each key in this database
is a document (article) ID; the corresponding value is the offset into 
.I artvec.bin
at which the vector for the document with that ID can be found.
In a single-file corpus, a document ID is the offset into the corpus
file at which the document begins.  In a multiple-file corpus, a
document ID is an key into the 
.I number2name
DBM (see 
.BR prepare_corpus (1))
that can be used to retrieve the document's filename.
The 
.I art2offset
 DBM and
.I artvec.bin
can be used to retrieve a document's vector given its ID.
.RE

.I offset2art.{dir,pag}
.RS
These two files make up a DBM database.  Each key in this database
is an offset into 
.I artvec.bin
at which a document vector begins.  The corresponding value is the
document ID of the document having that vector.  This DBM and
.I artvec.bin
can be used to retrieve a document given its vector.
.RE

.SH SEE ALSO
.BR prepare_corpus (1), \ count_wordvec (1), \ svdinterface (1), \
\ encode_wordvec (1), \ write_text_params (1).

.SH DIAGNOSTICS
Returns 0 to indicate success; 1 to indicate error.

.SH BUGS
Please report bugs to 
.BR [e-mail] .

.SH CREDITS
The Infomap NLP software was written by Stefan Kaufmann, Hinrich
Schuetze, Dominic Widdows, Beate Dorow, and Scott Cederberg.  The
Infomap algorithm was originally developed by Hinrich Schuetze.

.SH AUTHOR
This manual page was written by Scott Cederberg.  Please direct
inquiries and bug reports to 
.BR [e-mail] .