Search

In this paper, we describe a reversible letter-to-sound/sound to-letter generation system based on an approach which combines a rule-based formalism with data-driven techniques. We adopt a probabilistic parsing strategy to provide a hierarchical lexical analysis of a word, including information such as morphology, stress, syllabification, phonemics and graphemics. Long-distance constraints are propagated by enforcing local constraints throughout the hierarchy. Our training and testing corpora are derived from the high-frequency portion of the Brown Corpus (10,000 words), augmented with markers indicating stress and word morphology. We evaluated our performance based on an unseen test set. The percentage of nonparsable words for letter-to-sound and sound-to-letter generation were 6% and 5% respectively. Of the remaining words our system achieved a word accuracy of 71.8% and a phoneme accuracy of 92.5% for letter-to-sound generation, and a word accuracy of 55.8% and letter accuracy of 89.4% for sound-to-letter generation. We also compared our hierarchical approach with an alternative, single-layer approach to demonstrate how the hierarchy provides a parsimonious description for English orthographic-phonological regularities, while simultaneously attaining competitive generation accuracy., Supported in part by DARPA.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima, Corp., Beavercreek, OH.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The Department of Defense (DoD) Air Force Continuous Acquisition and Life cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DOD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax using several commercial and public domain SGML parsers prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test was to analyze the Standard Generalize Markup Language (SGML) syntax of the submitted Document Type Definition (DTD) MIL-M-38784C supplement, developed by the Air Force Technical Manuals Specifications and Standards (TMSS) program, prior to placing the DTD in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305603

The Department of Defense (DOD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, NIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DOD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Elecronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CAtS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DOD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CAtS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CAtS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results.

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion suite of military specifications. The AFCTN is a DOD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DOD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH, Contract No. DCA100-93-D-0065. ADA305590 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 6, Prepared in collaboration with Maxima Corp., Beavercreek, OH Contract No. DCA100-93-D-0065. ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305596 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion suite of military specifications. The AFCTN is a DOD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government intepretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results., Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH, Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-1840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results. (KAR) p. 7, Prepared in collaboration with Maxima Corp., Beavercreek, OH., Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305594 ADA305595 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion. suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results., Prepared in collaboration with Maxima Corp., Beavercreek, OH, Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305592 ADA305593 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The Department of Defense (DoD) Air Force Continuous Acquisition and Life-cycle Support (CALS) Test Network (AFCTN) is conducting tests of the military standard for the Automated Interchange of Technical Information, MIL-STD-l840A, and its companion suite of military specifications. The AFCTN is a DoD sponsored confederation of voluntary participants from industry and government managed by the Electronic Systems Center (ESC). The primary objective of the AFCTN is to evaluate the effectiveness of the CALS standards for technical data interchange and to demonstrate the technical capabilities and operational suitability of those standards. Two general categories of tests are performed to evaluate the standards; formal and informal. Formal tests are large and comprehensive, which follow a written test plan, require specific authorization from the DoD, and may take months to prepare, execute, and report. Informal tests are quick and short, used by the AFCTN technical staff, to broaden the testing base. They include representative samples of the many systems and applications used by AFCTN participants. They also allow the AFCTN staff to gain feedback from many industry and government interpretations of the standards, to increase the base of participation in the CALS initiative, and respond to the many requests for help that come from participants. Participants take part voluntarily, benefit by receiving an evaluation of their latest implementation (interpretation) of the standards, interact with the AFCTN technical staff, gain experience using the standards, and develop increased confidence in them. The results of informal tests are reported in Quick Short Test Reports (QSTRs) that briefly summarize the standard(s) tested, the hardware and software used, the nature of the test, and the results., Prepared in collaboration with Maxima Corp., Beavercreek, OH, Contract No. DCA100-93-D-0065. ADA305590 ADA305591 ADA305593 ADA305594 ADA305595 ADA305596 ADA305597 ADA305598 ADA305599 ADA305600 ADA305601 ADA305602 ADA305603

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH. ADA306309 ADA306310 ADA306311 ADA306312 ADA306313 ADA306315 ADA306316

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH. ADA306309 ADA306311 ADA306312 ADA306313 ADA306314 ADA306315 ADA306316

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH. ADA306309 ADA306310 ADA306311 ADA306312 ADA306314 ADA306315 ADA306316

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH. ADA306309 ADA306310 ADA306312 ADA306313 ADA306314 ADA306315 ADA306316

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH. ADA306309 ADA306310 ADA306311 ADA306313 ADA306314 ADA306315 ADA306316

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository., Prepared in collaboration with Maxima Corp., Beavercreek, OH. ADA306309 ADA306310 ADA306311 ADA306312 ADA306313 ADA306314 ADA306316

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository.

The purpose of this informal test is to analyze Air Force Document Type Definitions (DTDs) for Standard Generalized Markup Language (SGML) syntax, using several commercial and public domain SGML parsers, prior to placing them in the Defense Information Systems Agency (DISA) Asset Source for Software Engineering Technology (ASSET) repository. (KAR) p. 7

This research examines the interaction of acoustic and lexical information in the identification of words in lexically ambiguous phoneme sequences. In Experiment 1, subjects show priming for the meaning of a large word like tulips when presented with a sequence of combinable short words like two lips. In Experiment 2 priming is found for the meaning of the second short word in similar sequences (e.g. lips in two lips ). Finally, Experiment 3 demonstrates that listeners do not show priming for a short word like lips when it is pronounced as part of a larger word like tulips. The results of these experiments show that listeners sometimes access words other than those intended by speakers, and that they may simultaneously access words associated with several alternative parses of ambiguous sequences. Furthermore, they suggest that acoustic marking of word onsets places constraints on the success of lexical access. To account for these results, we present a new model of lexical access and segmentation, the Good Start model, which gives a principled account of these properties.

The design and implementation of an incremental recompilation manager (IRM) for Standard ML of New Jersey (SML/NJ) is described. Truly separate compilation is difficult to implement correctly and efficiently for SML because one compilation unit may depend not only on the interface of another, but also on its implementation. In this paper we present an integrated compilation system based on the visible compiler primitives provided by SML/NJ that supports 'smart recompilation to minimize system build time in most situations. Large systems are presented as hierarchical source groups. An automatic dependency analyzer determines constraints on the order in which sources must be considered. By abstracting away from the specifics of the SML/NJ compiler, the IRM readily generalizes to arbitrary 'compilation tools' such as parser generators and embedded languages.

The Proteus system which we have used for MUC-5 is largely unchanged from that used for MUC-3 and MUC-4. It has three main components: a syntactic analyzer, a semantic analyzer, and a template generator. The Proteus syntactic analyzer was developed starting in the fall of 1984 as a common base for all the applications of the Proteus Project. Many aspects of its design reflect its heritage in the Linguistic String Parser, previously developed and still in use at New York University. The current system, including the Restriction Language compiler, the lexical analyzer, and the parser proper, comprise approximately 4500 lines of Common Lisp. The semantic analyzer was initially developed in 1987 for the MUCK-I (RAINFORMs) application, extended for the MUCK-II (OPREPS) application, and has been incrementally revised since. It currently consists of about 3000 lines of Common Lisp (excluding the domain-specific information). The template generator was written from scratch for the MUC-5 joint venture task; it is about 1200 lines of Common Lisp., Presented at the Message Understanding Conference (5th), held in Baltimore, MD, on 25-27 Aug 1993. Published in the Proceedings of the Message Understanding Conference (5th), Paper M93-1016, p181-194, 1993. Sponsored in part by Advanced Research Projects Agency (ARPA).

Traditional approaches to the problem of extracting data from texts have emphasized hand-crafted linguistic knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of an ARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques. Our research and development goals are: * more rapid development of new applications, * the ability to train (and re-train) systems based on user markings of correct and incorrect output, * more accurate selection among interpretations when more than one is found, and * more robust partial interpretation when no complete interpretation can be found. We began this research agenda approximately three years ago. During the past two years, we have evaluated much of our effort in porting our data extraction system (PLUM) to a new language (Japanese) and to two new domains. Three key design features distinguish PLUM: statistical language modeling, learning algorithms and partial understanding. The first key feature is the use of statistical modeling to guide processing. For the version of PLUM used in MUC-5, part of speech information was determined by using well-known Markov modeling techniques embodied in BBN's part-of-speech tagger POST [5]. We also used a correction model, AMED [3], for improving Japanese segmentation and part-of-speech tags assigned by JUMAN. For the microelectronics domain, we used a probabilistic model to help identify the role of a company in a capability (whether it is a developer, user, etc.). Statistical modeling in PLUM contributes to portability, robustness, and trainability. The second key feature is our use of learning algorithms both to obtain the knowledge bases used by PLUM's processing modules and to train the probabilistic algorithms. A third key feature is partial understanding. All components of PLUM are designed to operate on partially interpretable input., Presented at the Message Understanding Conference (5th) (MUC-5), held in Baltimore, MD on 25-27 August 1993. Pub. in the Proceedings of the Message Understanding Conference (5th) (MUC-5), 1993. Paper M93-1010.

This paper describes the GE-CMU TIPSTER/SHOGUN system as configured for the TIPSTER 24-month (MUC-5) benchmark, and gives details of the system's performance on the selected Japanese and English texts. The SHOGUN system is a distillation of some of the key ideas that emerged from previous benchmarks and experiments, emphasizing a simple architecture in which the focus is on detailed corpus-based knowledge . This design allowed the project to meet its goal of achieving advances in coverage and accuracy while showing consistently good performance across languages and domains., Presented at the Conference on Message Understanding (5th), held in Baltimore, MD on 25-27 Aug 1993. Pub. in the Proceedings of the Conference on Message Understanding (5th), p109-120, 1993, Sponsored in part by DARPA.

Traditional approaches to the problem of extracting data from texts have emphasized hand-crafted linguistic knowledge In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of an ARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques. Our research and development goals are: * Achieving high performance in objective evaluations, such as the Tipster evaluations. * Reducing human effort in porting the natural language algorithms to new domains and to new languages. * Providing technology that is scalable to realistic applications. We began this research agenda approximately three years ago. During the past two years, we have ported our data extraction system (PLUM) to a new language (Japanese) and to two new domains., Presented at the Tipster Text (Phase I) 24-Month Conference held in Fredericksburg, VA in 1993. Pub. in the Proceedings of the Tipster Text (Phase I) 24-Month Conference, 1993. Sponsored in part by the Defense Advanced Research Projects Agency (DARPA).

This thesis presents NL-Soar, a detailed computational model of human sentence comprehension that accounts for a broad range of psycholinguistic phenomena. NL-Soar provides in-depth accounts of structural ambiguity resolution, garden path effects, unproblematic ambiguities, parsing breakdown on difficult embeddings, acceptable embeddings, immediacy of interpretation, and the time course of comprehension. The model explains a variety of both modular and interactive effects, and shows how learning can affect ambiguity resolution behavior. In addition to accounting for the qualitative phenomena surrounding parsing breakdown and garden path effects, NL-Soar explains a wide range of contrasts between garden paths and unproblematic ambiguities, and difficult and acceptable embeddings: the theory has been applied in detail to over 100 types of structures representing these contrasts, with a success rate of about 90%. The account of real-time immediacy includes predictions about the time course of comprehension and a zero-parameter prediction about the average rate of skilled comprehension. Finally, the theory has been successfully applied to a suggestive range of cross-linguistic examples, including constructions from head-final languages such as Japanese.

The User-Assisted Translation of Operational Plans (UATOP) project and Anticipating Combat Ammunition Consumption (ACAC) project are building tools to assist Division Ammunition Officers (DAOs) in anticipating ammunition consumption before battle. This capability is a vital component of logistics operations in the Army's emerging AirLand Operations doctrine. Operating with future Army information systems, the program will examine operation orders (OPORDs) and simulate the battle and potential courses of action to estimate consumption quantity and location of high-cost, high-weight munitions. Significantly improving the DAO's capability will increase combat unit effectiveness by minimizing the amount of extra ammunition that must be carried by a unit if oversupplied, thus freeing up vehicles and enabling more rapid deployment. Likewise, the system will pinpoint potential undersupply problems before the battle. A key to the ACAC simulation technology is the ability for the simulation to "understand" the contents of OPORDs. This includes establishing task force organization and locating and translating the tasks to perform. Because OPORDs contain English directives written for people and not machines, current machine-translation techniques are not directly suitable for extracting OPORD data. RAND has developed a new machine-translation approach that takes advantage of the prescribed 5-paragraph format of OPORDs to identify and isolate pertinent pieces of information. This approach uses concise and clear rules to antomatically generate programs that take as input textual OPORDs, such as those transmitted through the Maneuver Control System (MCS), extracts the desired data, and outputs this data as input to other computer systems. This report describes the structure and operation of the OPORG translation system. (9 figures, 12 refs.), ISBN-0-8330-2010-2.