The Process of Question Answering.

reportActive / Technical Report | Accession Number: ADA040559 | Open PDF

Abstract:

Problems in computational question answering assume a new perspective when question answering is viewed as a problem in natural language processing. A theory of question answering has been proposed which relies on ideas in conceptual information processing and theories of human memory organization. This theory of question answering has been implemented in a computer program, QUALM, currently being used by two story understanding systems to complete a natural language processing system which reads stories and answers questions about what was read. The processes in QUALM are divided into 4 phases 1 Conceptual categorization which guides subsequent processing by dictating which specific inference mechanisms and memory retrieval strategies should be invoked in the course of answering a question 2 Inferential analysis which is responsible for understanding what the questioner really meant when a question should not be taken literally 3 Content specification which determines how much of an answer should be returned in terms of detail and elaborations, and 4 Retrieval heuristics which do the actual digging to extract an answer from memory.

Author(s):
Lehnert, Wendy G.
Author Organization(s):
YALE UNIV NEW HAVEN CONN DEPT OF COMPUTER SCIENCE
Descriptive Note:
Research rept.,
Supplementary Note:
Doctoral thesis.
Pagination:
0295

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
RR-88
Contract/Grant Number(s):
N00014-75-C-1111
 Subject Terms
Joint Capability Areas:
JCA_5_Command and Control; JCA_5.3_Planning; JCA_1.2.6_Concepts; JCA_8_Building Partnerships; JCA_1_Force Support; JCA_8.2_Shape; JCA_1.2_Force Preparation; JCA_2_Battlespace Awareness; JCA_2.3_Processing and Exploitation; JCA_5.3.2_Apply Situational Understanding; JCA_5.3.3_Develop Strategy; JCA_8.2.2_Provide Aid to Foreign Partners and Institutions; JCA_8.2.1_Partner with Governments and Institutions; JCA_8.1.3_Influence Adversary and Competitor Audiences; JCA_8.1_Communicate; JCA_5.2.2_Develop Knowledge and Situational Awareness; JCA_5.2_Understand; JCA_5.5_Direct; JCA_1.2.1_Training; JCA_5.5.1_Communicate Intent and Guidance; JCA_5.5.3_Establish Metrics
Modernization Areas:
Fully Networked C3; AI and Machine Learning
Communities of Interest:
C4I
Descriptor(s):
*EXPERIMENTAL DESIGN, *INTERROGATION, *NATURAL LANGUAGE, *INFORMATION PROCESSING, COMPUTER PROGRAMS, COMPUTERIZED SIMULATION, SOCIAL COMMUNICATION, MEMORY(PSYCHOLOGY), THESES, INFORMATION RETRIEVAL, CLASSIFICATION, HEURISTIC METHODS, PATTERN RECOGNITION, ARTIFICIAL INTELLIGENCE, AMBIGUITY, TEXT PROCESSING, MACHINE TRANSLATION, COMPREHENSION
Field(s)/Group(s):
Linguistics, Psychology, Computer Programming and Software, Bionics
Keyword(s):
*Qualm computer program, *Question answering systems, Cognition, Inference, Story comprehension, Understanding, Dialog(Computers)
Report Date:
1977 May 01