Collaborative human-machine analysis using a controlled natural language

David H. Mott, Donald R. Shemanski, Cheryl Giammanco, Dave Braines

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

6 Citations (Scopus)

Abstract

A key aspect of an analyst's task in providing relevant information from data is the reasoning about the implications of that data, in order to build a picture of the real world situation. This requires human cognition, based upon domain knowledge about individuals, events and environmental conditions. For a computer system to collaborate with an analyst, it must be capable of following a similar reasoning process to that of the analyst. We describe ITA Controlled English (CE), a subset of English to represent analyst's domain knowledge and reasoning, in a form that it is understandable by both analyst and machine. CE can be used to express domain rules, background data, assumptions and inferred conclusions, thus supporting human-machine interaction. A CE reasoning and modeling system can perform inferences from the data and provide the user with conclusions together with their rationale. We present a logical problem called the "Analysis Game", used for training analysts, which presents "analytic pitfalls"' inherent in many problems. We explore an iterative approach to its representation in CE, where a person can develop an understanding of the problem solution by incremental construction of relevant concepts and rules. We discuss how such interactions might occur, and propose that such techniques could lead to better collaborative tools to assist the analyst and avoid the "pitfalls"'.

Original languageEnglish (US)
Title of host publicationNext-Generation Analyst III
EditorsTimothy P. Hanratty, James Llinas, Barbara D. Broome, David L. Hall
PublisherSPIE
Volume9499
ISBN (Electronic)9781628416152
DOIs
StatePublished - Jan 1 2015
EventNext-Generation Analyst III - Baltimore, United States
Duration: Apr 20 2015Apr 21 2015

Other

OtherNext-Generation Analyst III
CountryUnited States
CityBaltimore
Period4/20/154/21/15

Fingerprint

Natural Language
Computer systems
Reasoning
Domain Knowledge
cognition
games
Human-machine Interaction
inference
set theory
education
Cognition
System Modeling
interactions
Person
Express
Game
Subset
Human
Interaction

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Mott, D. H., Shemanski, D. R., Giammanco, C., & Braines, D. (2015). Collaborative human-machine analysis using a controlled natural language. In T. P. Hanratty, J. Llinas, B. D. Broome, & D. L. Hall (Eds.), Next-Generation Analyst III (Vol. 9499). [94990J] SPIE. https://doi.org/10.1117/12.2180121
Mott, David H. ; Shemanski, Donald R. ; Giammanco, Cheryl ; Braines, Dave. / Collaborative human-machine analysis using a controlled natural language. Next-Generation Analyst III. editor / Timothy P. Hanratty ; James Llinas ; Barbara D. Broome ; David L. Hall. Vol. 9499 SPIE, 2015.
@inproceedings{1cc14ec1380f47dbbb59892e17d656dc,
title = "Collaborative human-machine analysis using a controlled natural language",
abstract = "A key aspect of an analyst's task in providing relevant information from data is the reasoning about the implications of that data, in order to build a picture of the real world situation. This requires human cognition, based upon domain knowledge about individuals, events and environmental conditions. For a computer system to collaborate with an analyst, it must be capable of following a similar reasoning process to that of the analyst. We describe ITA Controlled English (CE), a subset of English to represent analyst's domain knowledge and reasoning, in a form that it is understandable by both analyst and machine. CE can be used to express domain rules, background data, assumptions and inferred conclusions, thus supporting human-machine interaction. A CE reasoning and modeling system can perform inferences from the data and provide the user with conclusions together with their rationale. We present a logical problem called the {"}Analysis Game{"}, used for training analysts, which presents {"}analytic pitfalls{"}' inherent in many problems. We explore an iterative approach to its representation in CE, where a person can develop an understanding of the problem solution by incremental construction of relevant concepts and rules. We discuss how such interactions might occur, and propose that such techniques could lead to better collaborative tools to assist the analyst and avoid the {"}pitfalls{"}'.",
author = "Mott, {David H.} and Shemanski, {Donald R.} and Cheryl Giammanco and Dave Braines",
year = "2015",
month = "1",
day = "1",
doi = "10.1117/12.2180121",
language = "English (US)",
volume = "9499",
editor = "Hanratty, {Timothy P.} and James Llinas and Broome, {Barbara D.} and Hall, {David L.}",
booktitle = "Next-Generation Analyst III",
publisher = "SPIE",
address = "United States",

}

Mott, DH, Shemanski, DR, Giammanco, C & Braines, D 2015, Collaborative human-machine analysis using a controlled natural language. in TP Hanratty, J Llinas, BD Broome & DL Hall (eds), Next-Generation Analyst III. vol. 9499, 94990J, SPIE, Next-Generation Analyst III, Baltimore, United States, 4/20/15. https://doi.org/10.1117/12.2180121

Collaborative human-machine analysis using a controlled natural language. / Mott, David H.; Shemanski, Donald R.; Giammanco, Cheryl; Braines, Dave.

Next-Generation Analyst III. ed. / Timothy P. Hanratty; James Llinas; Barbara D. Broome; David L. Hall. Vol. 9499 SPIE, 2015. 94990J.

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

TY - GEN

T1 - Collaborative human-machine analysis using a controlled natural language

AU - Mott, David H.

AU - Shemanski, Donald R.

AU - Giammanco, Cheryl

AU - Braines, Dave

PY - 2015/1/1

Y1 - 2015/1/1

N2 - A key aspect of an analyst's task in providing relevant information from data is the reasoning about the implications of that data, in order to build a picture of the real world situation. This requires human cognition, based upon domain knowledge about individuals, events and environmental conditions. For a computer system to collaborate with an analyst, it must be capable of following a similar reasoning process to that of the analyst. We describe ITA Controlled English (CE), a subset of English to represent analyst's domain knowledge and reasoning, in a form that it is understandable by both analyst and machine. CE can be used to express domain rules, background data, assumptions and inferred conclusions, thus supporting human-machine interaction. A CE reasoning and modeling system can perform inferences from the data and provide the user with conclusions together with their rationale. We present a logical problem called the "Analysis Game", used for training analysts, which presents "analytic pitfalls"' inherent in many problems. We explore an iterative approach to its representation in CE, where a person can develop an understanding of the problem solution by incremental construction of relevant concepts and rules. We discuss how such interactions might occur, and propose that such techniques could lead to better collaborative tools to assist the analyst and avoid the "pitfalls"'.

AB - A key aspect of an analyst's task in providing relevant information from data is the reasoning about the implications of that data, in order to build a picture of the real world situation. This requires human cognition, based upon domain knowledge about individuals, events and environmental conditions. For a computer system to collaborate with an analyst, it must be capable of following a similar reasoning process to that of the analyst. We describe ITA Controlled English (CE), a subset of English to represent analyst's domain knowledge and reasoning, in a form that it is understandable by both analyst and machine. CE can be used to express domain rules, background data, assumptions and inferred conclusions, thus supporting human-machine interaction. A CE reasoning and modeling system can perform inferences from the data and provide the user with conclusions together with their rationale. We present a logical problem called the "Analysis Game", used for training analysts, which presents "analytic pitfalls"' inherent in many problems. We explore an iterative approach to its representation in CE, where a person can develop an understanding of the problem solution by incremental construction of relevant concepts and rules. We discuss how such interactions might occur, and propose that such techniques could lead to better collaborative tools to assist the analyst and avoid the "pitfalls"'.

UR - http://www.scopus.com/inward/record.url?scp=84954072132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954072132&partnerID=8YFLogxK

U2 - 10.1117/12.2180121

DO - 10.1117/12.2180121

M3 - Conference contribution

VL - 9499

BT - Next-Generation Analyst III

A2 - Hanratty, Timothy P.

A2 - Llinas, James

A2 - Broome, Barbara D.

A2 - Hall, David L.

PB - SPIE

ER -

Mott DH, Shemanski DR, Giammanco C, Braines D. Collaborative human-machine analysis using a controlled natural language. In Hanratty TP, Llinas J, Broome BD, Hall DL, editors, Next-Generation Analyst III. Vol. 9499. SPIE. 2015. 94990J https://doi.org/10.1117/12.2180121