ontolog-forum
[Top] [All Lists]

[ontolog-forum] Patent application for using a formal ontology in NLP

To: "[ontolog-forum]" <ontolog-forum@xxxxxxxxxxxxxxxx>
From: "John F. Sowa" <sowa@xxxxxxxxxxx>
Date: Wed, 01 Sep 2010 14:24:33 -0400
Message-id: <4C7E9A61.9090307@xxxxxxxxxxx>
A certain Werner Ceusters and his buddies have been submitting
patent applications that cover almost every NLP system implemented
in the past half century.    (01)

One of their applications for using conceptual graphs to extract
meaning from a text was actually granted, despite the fact that
there were hundreds of publications dating back to 1976.  See    (02)

http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=%22ceusters,+werner%22.INNM.&OS=IN/    (03)

The same first "inventor" plus two others submitted another
application that covers any use of a computer for "referent
tracking of portions of reality."  It is broad enough to cover
any program that resolves anaphoric references in documents:    (04)

http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=1&p=1&f=G&l=50&d=PG01&S1=20090055437&OS=20090055437&RS=20090055437    (05)

I had previously sent messages about these two patents to Corpora List,
which includes many computational linguists.  But I also came across
another patent application by the same first "inventor" that covers
any use of a formal ontology for "natural language understanding."    (06)

Following is a copy of the note that I sent to Corpora List.    (07)

John Sowa    (08)

-------- Original Message --------
Subject: [Corpora-List] Patent application for using an ontology
in "natural language understanding"
Date: Wed, 01 Sep 2010 13:48:04 -0400
From: John F. Sowa <sowa@xxxxxxxxxxx>
To: corpora@xxxxxx    (09)

I received an offline note that pointed to another application
by Werner Ceusters et al., which is broad enough to cover any use
of "concepts included in a computer implemented formal ontology and
arranged in a hierarchy."    (010)

They filed this application as a continuation to the previously
granted patent that used conceptual graphs.  But they broadened
it to a cover a wider range of systems.  (See excerpts below.)    (011)

Note that there is a little dialog box at the end of the web page
at the URL below.  It allows people to comment on this so-called
invention.    (012)

Anybody who knows of relevant prior art might use that dialog
box to send them a message.  I don't know what effect those
comments might have, but I hope that they might influence
the patent examiners.    (013)

John Sowa
___________________________________________________________________    (014)

http://www.faqs.org/patents/app/20090259459    (015)

Patent application title: CONCEPTUAL WORLD REPRESENTATION NATURAL
LANGUAGE UNDERSTANDING SYSTEM AND METHOD    (016)

Inventors:  Werner Ceusters  Mick O'Donnell  Frank Montyne  Frederik
Coppens  Maarten Van Mol    (017)

Patent application number: 20090259459    (018)

Abstract:    (019)

A Natural Language Understanding system is provided for indexing of free
text documents. The system according to the invention utilizes
typographical and functional segmentation of text to identify those
portions of free text that carry meaning. The system then uses words and
multi-word terms and phrases identified in the free to text to identify
concepts in the free text. The system uses a lexicon of terms linked to
a formal ontology that is independent of a specific language to extract
concepts from the free text based on the words and multi-word terms in
the free text. The formal ontology contains both language independent
domain knowledge concepts and language dependent linguistic concepts
that govern the relationships between concepts and contain the rules
about how language works. The system according to the current invention
may preferably be used to index medical documents and assign codes from
independent coding systems, such as, SNOMED, ICD-9 and ICD-10. The
system according to the current invention may also preferably make use
of syntactic parsing to improve the efficiency of the method.    (020)

Claims:    (021)

1. A computer-readable medium storing code representing instructions
that when executed by a computer cause the computer to:receive as an
input at least a portion of a document;extract a meaning contained in
the portion of the document based on a comparison of the portion to a
plurality of concepts included in a computer implemented formal ontology
and arranged in a hierarchy, said hierarchy having a primary concept
defined based on a set of criteria, each concept from the plurality of
concepts hierarchically linked to and below the primary concept being
defined based on all criteria from the set of criteria and based on at
least one additional criterion different than each criterion from the
set of criteria; andindex the portion of the document based on said
meaning extracted from the portion of the document.    (022)


_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/  
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/  
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/ 
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx    (023)

<Prev in Thread] Current Thread [Next in Thread>