|
COMMERCE BUSINESS DAILY ISSUE OF OCTOBER 3,1996 PSA#1693Defense Advanced Research Projects Agency (DARPA), Contracts Management
Office (CMO), 3701 N. Fairfax Dr., Arlington VA 22203-1714 A -- HIGH PERFORMANCE KNOWLEDGE BASES (HPKB) SOL BAA 96-43 DUE 120296
POC David Gunning, DARPA/ISO, FAX: (703) 696-2203. The goal of the
High-Performance Knowledge Base (HPKB) program is to produce the
technology needed to enable system developers to rapidly (within
months) construct large (100K-1M axiom/rule/frame) knowledge-bases that
provide comprehensive coverage of topics of interest, are reusable by
multiple applications with diverse problem-solving strategies, and are
maintainable in rapidly changing environments. It is envisioned that
the process for constructing these large, comprehensive, reusable, and
maintainable knowledge bases would involve three major steps: Building
Foundation Knowledge: creating the foundation knowledge (e.g.,
selecting the knowledge representation scheme, assembling theories of
common knowledge, defining domain-specific terms and concepts) to
enable the construction and population of large, comprehensive
knowledge bases for particular domains of interest -- by selecting,
composing, extending, specializing, and modifying components from a
library of reusable ontologies, common domain theories, and generic
problem-solving strategies Acquiring Domain Knowledge: constructing and
populating a complete knowledge base -- by using the foundation
knowledge to generate domain-specific knowledge acquisition, data
mining, and information extraction tools -- to enable collaborating
teams of domain (non-computer) experts to easily extend the foundation
theories, define additional domain theories and problem solving
strategies, and acquire domain facts to populate a comprehensive
knowledge base covering the domains of interest.Efficient Problem
Solving: enabling efficient problem solving -- either by providing
efficient inference and reasoning procedures to operate on a complete
knowledge base, or by providing tools and techniques to select and
transform knowledge from a complete knowledge base into optimized
problem-solving modules tailored to the unique requirements of an
application. The objective of HPKB is to develop, integrate, and test
the technology needed to enable this process, in a four-year
development program, beginning in 1997 and running through September,
2000. The intention is to produce, by the end of FY00, alternative
knowledge-base development environments, which combine the necessary
foundation-building, knowledge-acquisition, and problem-solving
technologies into an integrated development environment, and to use
those environments to build reusable knowledge-base components for
multiple DARPA application projects. The candidate applications are a
set of new and on-going DARPA initiatives, all of which are building
advanced information systems to improve some aspect of military
operations, and all of which need knowledge-rich components to reason
about and understand the battlefield or crisis situation. The candidate
projects are: Dynamic Multi-user Information Fusion (DMIF), Joint Task
Force (JTF) Advanced Technology Demonstration (ATD), Technology
Development for the Joint Force Air Component Commander (JFACC),
Advanced Logistics Program (ALP), Battlefield Awareness Data
Dissemination (BADD), and Information Gathering, Processing and
Analyses in Support of Crisis Management (Project Genoa). The HPKB
program intends to produce multiple knowledge-base development
environments and exercise them to build knowledge-base components for
these applications. The approach for achieving this objective is to:
(1) develop individual foundation-building, knowledge-acquisition, and
problem-solving technologies, (2) integrate those individual
technologies into two or more integrated knowledge-base development
environments, (3) develop a set of test ''challenge problems'' which
reflect the knowledge-base requirements of the application projects,
(4) evaluate the alternative knowledge-base technologies and integrated
development environments against those test problems, and, in the
process (5) produce knowledge-base components for use by the
application projects. These efforts will occur in parallel, with more
effort initially going into tasks #1 and #2 and more effort on task #5
later in the project. The cornerstone of this approach -- the bridge
between technology development and application -- is the set of
''challenge problems'' which will be used to focus research and
development efforts and measure the effectiveness of alternative
technical approaches. Challenge problem test sets will be developed to
be representative of knowledge-base requirements from the candidate
applications. These test sets will be used as the basis for annual
evaluations of the developing technology. Developers will be asked to
build test knowledge bases to satisfy specific test problem
specifications. As a part of the evaluation, the completeness and
correctness of the developed knowledge base will be measured, as well
as the time required to build the knowledge base and the ease of
modifying the knowledge base to assimilate new or changed knowledge.
The results of the evaluation will be reported and discussed in a
subsequent conference and used to stimulate sharing and interchange of
promising technical approaches among the research community. These
challenge problems have not been defined in detail, nor have the
specific evaluation metrics or evaluation processes, DARPA is also
soliciting, in this BAA, proposals to define, develop, and maintain the
challenge problem test sets for the HPKB program. Successful proposals
in the technology development and integration category will be
expected to propose effort to participate in the annual challenge
problem evaluations. It is estimated that the evaluation will require
development teams to spend one month during each annual evaluation,
using their newly developed tools and techniques to build test
knowledge bases to satisfy the specified challenge problems. The first
evaluation will be held approximately one year after contract award.
After an initial analysis of the candidate applications, two classes of
challenge problems were identified that will be refined to create the
specific challenge problem test sets. The two challenge problems will
be based on developing: (1) comprehensive battlefield knowledge (e.g.,
terrain characteristics, force structures, military organizations,
troop movements, military strategy, transportation and logistics
operations) to provide in-depth reasoning to support situation
assessment, air campaign planning, and logistics planning, and (2)
general knowledge for information retrieval and intelligence analysis,
involving the development of a broader, more general knowledge base,
suited for information retrieval from a wide variety of general
information sources, such as the Internet. Through these challenge
problems, HPKB technology developers will build and test knowledge-base
tools and use them to incrementally build products for possible
insertion into the application projects. To support this process DARPA
is soliciting, under this BAA, one, two, or three year proposals in
the following two categories: (1) Knowledge-Base Technology Development
and Integration, to develop the individual foundation-building,
knowledge-acquisition, and problem-solving technologies, as well as
combine those technologies into integrated knowledge-base development
environments, and (2) Challenge Problem Development and Evaluation
Management, to define, develop, and maintain the challenge problem test
sets, as well as defining and managing the annual evaluation process
and evaluation conferences. GENERAL INFORMATION. An industry briefing
will be held on 11 OCT 1996. Final proposals are due on 2 DEC 1996.
Proposers must submit an original and 10 copies of full proposals to
DARPA/ISO, 3701 North Fairfax Drive, Arlington, VA 22203-1714, (ATTN:
BAA 96-43) by 4:00 PM, 2 DEC 1996, in order to be considered. Proposers
must obtain a pamphlet, BAA 96-43 Proposer Information, which provides
further information on areas of interest, the submission, evaluation,
funding processes, and proposal formats. This pamphlet may be obtained
by electronic mail, world-wide web, or mail request to the
administrative contact address given below. Proposals not meeting the
format described in the pamphlet may not be reviewed. This notice, in
conjunction with the pamphlet BAA 96-43 Proposer Information,
constitutes the total BAA. No additional information is available, nor
will a formal RFP or other solicitation regarding this announcement be
issued. Requests for same will be disregarded. The Government reserves
the right to select for award all, some, or none of the proposals
received. All responsible sources capable of satisfying the
Government's needs may submit a proposal which shall be considered.
Historically Black Colleges and Universities (HBCU) and Minority
Institutions (MI) are encouraged to submit proposals and join others in
submitting proposals, however, no portion of this BAA will be set aside
for HBCU and MI participation due to the impracticality of reserving
discrete or several areas of research in this area of research. Awards
made under this BAA are subject to the provisions of the Federal
Acquisition Regulation (FAR) Subpart 9.5, Organizational Conflict of
Interest. All offerors and proposed subcontractors must affirmatively
state whether they are supporting any DARPA technical office(s) through
an active contract or subcontract. All affirmations must state which
office(s) the offeror supports, and identify the prime contract number.
Affirmations should be furnished at the time of proposal submission.
All facts relevant to the existence or potential existence of
organizational conflicts of interest, as that term is defined in FAR
9.501, must be disclosed. This disclosure shall include a description
of the action the Contractor has taken, or proposes to take, to avoid,
neutralize or mitigate such conflict. Evaluation of proposals will be
accomplished through a technical review of each proposal using the
following criteria, which are listed in descending order of relative
importance: (1) innovativeness of proposed solutions to meet program
objectives, (2) soundness of technical approach, (3) quality, quantity,
and experience of technical personnel, (4) soundness of program plan
and SOW, (5) cost realism. The annual budget available to fund
proposals from this BAA is approximately $8M per year. It is estimated
that $3-4M per year will be available for individual technology
developments, $2-4M for integrated development environments, and $1-2M
on developing and managing the challenge problem evaluations. It is
expected that individual technology efforts will range from $200K to
$600K per year, and that the integration efforts would range from $1M
to $2M per year, depending on the amount of component technology
development included. Administrative addresses for this BAA: All
administrative correspondence and questions on this solicitation,
including requests for information on how to submit a proposal to this
BAA, should be directed to one of the administrative addresses below,
e-mail or fax is preferred. DARPA intends to use electronic mail and
fax for correspondence regarding BAA 96-43. Proposals shall not be
submitted by fax, any so sent will be disregarded. Fax: (703) 696-2203,
Addressed to: David Gunning, DARPA/ISO, BAA 96-43, Electronic Mail:
baa96-43@darpa.mil, Electronic File Retrieval:
http://www.darpa.mil/baa/#iso, Mail:DARPA/ISO,ATTN: BAA 96-43, 3701N.
Fairfax Drive, Arlington, VA 22203-1714. SPONSOR: Defense Advanced
Research Projects Agency (DARPA), Contracts Management Office (CMO),
3701 North Fairfax Drive, Arlington, VA 22203-1714 SUBFILE: PSE (U.S.
GOVERNMENT PROCUREMENTS, SERVICES) SECTION HEADING: A Research and
Development (0275) Loren Data Corp. http://www.ld.com (SYN# 0002 19961002\A-0002.SOL)
A - Research and Development Index Page
|
|