Field-effect natural language semantic mapping

Stuart H. Rubin, Shu Ching Chen, Mei-Ling Shyu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper addresses the problem of mapping natural language to its semantics. It presupposes that the input is in random (compressed) form and proceeds to detail a methodology for extracting the semantics from that normal form. The idea is to enumerate contextual cues and learn to associate those cues with meaning. The process is inherently fuzzy and for this reason is also inherently adaptive in nature, It is shown that the influence of context on meaning grows exponentially with the length of a word sequence. This suggests that rule-based randomization plays a key role in rendering a field-effect natural language semantic mapping tractable. An example of rule-based randomization for semantic normalization is as follows. Suppose that two commands to a robot are deemed lo be equivalent; namely, "Grasp and pick up the glass" and "Hold the cup and raise it". Their mutual normalization might then be, "Grab container. Lift container." Clearly, the randomization process can be effected by rules. Also, the normalized syntax makes the result of any semantic mapping process - such as detailed herein - more efficient. A natural language front-end is described, which is designed to reduce the impedance mismatch between the human and the machine. Most significantly, the effective translation of natural language semantics is shown to critically depend on an accelerated capability for learning.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Pages2483-2487
Number of pages5
Volume3
StatePublished - 2003
EventSystem Security and Assurance - Washington, DC, United States
Duration: Oct 5 2003Oct 8 2003

Other

OtherSystem Security and Assurance
CountryUnited States
CityWashington, DC
Period10/5/0310/8/03

Fingerprint

Semantics
Containers
Robots
Glass

Keywords

  • Machine learning
  • Natural language
  • Randomization
  • Translation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Rubin, S. H., Chen, S. C., & Shyu, M-L. (2003). Field-effect natural language semantic mapping. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 3, pp. 2483-2487)

Field-effect natural language semantic mapping. / Rubin, Stuart H.; Chen, Shu Ching; Shyu, Mei-Ling.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 3 2003. p. 2483-2487.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rubin, SH, Chen, SC & Shyu, M-L 2003, Field-effect natural language semantic mapping. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 3, pp. 2483-2487, System Security and Assurance, Washington, DC, United States, 10/5/03.
Rubin SH, Chen SC, Shyu M-L. Field-effect natural language semantic mapping. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 3. 2003. p. 2483-2487
Rubin, Stuart H. ; Chen, Shu Ching ; Shyu, Mei-Ling. / Field-effect natural language semantic mapping. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 3 2003. pp. 2483-2487
@inproceedings{4ef4d7b2f84a4cda817f2c81f9dc2653,
title = "Field-effect natural language semantic mapping",
abstract = "This paper addresses the problem of mapping natural language to its semantics. It presupposes that the input is in random (compressed) form and proceeds to detail a methodology for extracting the semantics from that normal form. The idea is to enumerate contextual cues and learn to associate those cues with meaning. The process is inherently fuzzy and for this reason is also inherently adaptive in nature, It is shown that the influence of context on meaning grows exponentially with the length of a word sequence. This suggests that rule-based randomization plays a key role in rendering a field-effect natural language semantic mapping tractable. An example of rule-based randomization for semantic normalization is as follows. Suppose that two commands to a robot are deemed lo be equivalent; namely, {"}Grasp and pick up the glass{"} and {"}Hold the cup and raise it{"}. Their mutual normalization might then be, {"}Grab container. Lift container.{"} Clearly, the randomization process can be effected by rules. Also, the normalized syntax makes the result of any semantic mapping process - such as detailed herein - more efficient. A natural language front-end is described, which is designed to reduce the impedance mismatch between the human and the machine. Most significantly, the effective translation of natural language semantics is shown to critically depend on an accelerated capability for learning.",
keywords = "Machine learning, Natural language, Randomization, Translation",
author = "Rubin, {Stuart H.} and Chen, {Shu Ching} and Mei-Ling Shyu",
year = "2003",
language = "English (US)",
volume = "3",
pages = "2483--2487",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

}

TY - GEN

T1 - Field-effect natural language semantic mapping

AU - Rubin, Stuart H.

AU - Chen, Shu Ching

AU - Shyu, Mei-Ling

PY - 2003

Y1 - 2003

N2 - This paper addresses the problem of mapping natural language to its semantics. It presupposes that the input is in random (compressed) form and proceeds to detail a methodology for extracting the semantics from that normal form. The idea is to enumerate contextual cues and learn to associate those cues with meaning. The process is inherently fuzzy and for this reason is also inherently adaptive in nature, It is shown that the influence of context on meaning grows exponentially with the length of a word sequence. This suggests that rule-based randomization plays a key role in rendering a field-effect natural language semantic mapping tractable. An example of rule-based randomization for semantic normalization is as follows. Suppose that two commands to a robot are deemed lo be equivalent; namely, "Grasp and pick up the glass" and "Hold the cup and raise it". Their mutual normalization might then be, "Grab container. Lift container." Clearly, the randomization process can be effected by rules. Also, the normalized syntax makes the result of any semantic mapping process - such as detailed herein - more efficient. A natural language front-end is described, which is designed to reduce the impedance mismatch between the human and the machine. Most significantly, the effective translation of natural language semantics is shown to critically depend on an accelerated capability for learning.

AB - This paper addresses the problem of mapping natural language to its semantics. It presupposes that the input is in random (compressed) form and proceeds to detail a methodology for extracting the semantics from that normal form. The idea is to enumerate contextual cues and learn to associate those cues with meaning. The process is inherently fuzzy and for this reason is also inherently adaptive in nature, It is shown that the influence of context on meaning grows exponentially with the length of a word sequence. This suggests that rule-based randomization plays a key role in rendering a field-effect natural language semantic mapping tractable. An example of rule-based randomization for semantic normalization is as follows. Suppose that two commands to a robot are deemed lo be equivalent; namely, "Grasp and pick up the glass" and "Hold the cup and raise it". Their mutual normalization might then be, "Grab container. Lift container." Clearly, the randomization process can be effected by rules. Also, the normalized syntax makes the result of any semantic mapping process - such as detailed herein - more efficient. A natural language front-end is described, which is designed to reduce the impedance mismatch between the human and the machine. Most significantly, the effective translation of natural language semantics is shown to critically depend on an accelerated capability for learning.

KW - Machine learning

KW - Natural language

KW - Randomization

KW - Translation

UR - http://www.scopus.com/inward/record.url?scp=0242721891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242721891&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0242721891

VL - 3

SP - 2483

EP - 2487

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

ER -