Integrating natural language generation and model-based reasoning for explanation generation

Donald Matheson*, George M. Coghill, Somayujulu Sripada

*Corresponding author for this work

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

Abstract

Natural Language Generation (NLG) systems can utilise external reasoning to explain events within a given domain. Most often, these explanations are derived from compiled knowledge such as that found in expert systems, which can lead to gaps in the explanation system's ability to justify the outcome of the reasoner. We propose the use of a deeper knowledge source for explanation generation and show how to utilise a model-based approach that uses first-principles knowledge of the problem domain to generate and justify more in-depth explanations of events in the domain. Our integrated framework of NLG and model-based reasoning makes two contributions: the articulation of model-based reasoning and justification in natural language, and the natural language generation engine exploiting the deeper knowledge available in the underlying model.

Original languageEnglish
Title of host publication2012 12th UK Workshop on Computational Intelligence, UKCI 2012
Number of pages7
DOIs
Publication statusPublished - 5 Dec 2012
Event2012 12th UK Workshop on Computational Intelligence, UKCI 2012 - Edinburgh, United Kingdom
Duration: 5 Sep 20127 Sep 2012

Conference

Conference2012 12th UK Workshop on Computational Intelligence, UKCI 2012
CountryUnited Kingdom
CityEdinburgh
Period5/09/127/09/12

Fingerprint

Expert systems
Engines

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics

Cite this

Integrating natural language generation and model-based reasoning for explanation generation. / Matheson, Donald; Coghill, George M.; Sripada, Somayujulu.

2012 12th UK Workshop on Computational Intelligence, UKCI 2012. 2012. 6335748.

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

Matheson, D, Coghill, GM & Sripada, S 2012, Integrating natural language generation and model-based reasoning for explanation generation. in 2012 12th UK Workshop on Computational Intelligence, UKCI 2012., 6335748, 2012 12th UK Workshop on Computational Intelligence, UKCI 2012, Edinburgh, United Kingdom, 5/09/12. https://doi.org/10.1109/UKCI.2012.6335748
Matheson, Donald ; Coghill, George M. ; Sripada, Somayujulu. / Integrating natural language generation and model-based reasoning for explanation generation. 2012 12th UK Workshop on Computational Intelligence, UKCI 2012. 2012.
@inproceedings{3effffd7b4d644c58272d621380ec91a,
title = "Integrating natural language generation and model-based reasoning for explanation generation",
abstract = "Natural Language Generation (NLG) systems can utilise external reasoning to explain events within a given domain. Most often, these explanations are derived from compiled knowledge such as that found in expert systems, which can lead to gaps in the explanation system's ability to justify the outcome of the reasoner. We propose the use of a deeper knowledge source for explanation generation and show how to utilise a model-based approach that uses first-principles knowledge of the problem domain to generate and justify more in-depth explanations of events in the domain. Our integrated framework of NLG and model-based reasoning makes two contributions: the articulation of model-based reasoning and justification in natural language, and the natural language generation engine exploiting the deeper knowledge available in the underlying model.",
author = "Donald Matheson and Coghill, {George M.} and Somayujulu Sripada",
year = "2012",
month = "12",
day = "5",
doi = "10.1109/UKCI.2012.6335748",
language = "English",
isbn = "9781467343923",
booktitle = "2012 12th UK Workshop on Computational Intelligence, UKCI 2012",

}

TY - GEN

T1 - Integrating natural language generation and model-based reasoning for explanation generation

AU - Matheson, Donald

AU - Coghill, George M.

AU - Sripada, Somayujulu

PY - 2012/12/5

Y1 - 2012/12/5

N2 - Natural Language Generation (NLG) systems can utilise external reasoning to explain events within a given domain. Most often, these explanations are derived from compiled knowledge such as that found in expert systems, which can lead to gaps in the explanation system's ability to justify the outcome of the reasoner. We propose the use of a deeper knowledge source for explanation generation and show how to utilise a model-based approach that uses first-principles knowledge of the problem domain to generate and justify more in-depth explanations of events in the domain. Our integrated framework of NLG and model-based reasoning makes two contributions: the articulation of model-based reasoning and justification in natural language, and the natural language generation engine exploiting the deeper knowledge available in the underlying model.

AB - Natural Language Generation (NLG) systems can utilise external reasoning to explain events within a given domain. Most often, these explanations are derived from compiled knowledge such as that found in expert systems, which can lead to gaps in the explanation system's ability to justify the outcome of the reasoner. We propose the use of a deeper knowledge source for explanation generation and show how to utilise a model-based approach that uses first-principles knowledge of the problem domain to generate and justify more in-depth explanations of events in the domain. Our integrated framework of NLG and model-based reasoning makes two contributions: the articulation of model-based reasoning and justification in natural language, and the natural language generation engine exploiting the deeper knowledge available in the underlying model.

UR - http://www.scopus.com/inward/record.url?scp=84870342630&partnerID=8YFLogxK

U2 - 10.1109/UKCI.2012.6335748

DO - 10.1109/UKCI.2012.6335748

M3 - Conference contribution

SN - 9781467343923

BT - 2012 12th UK Workshop on Computational Intelligence, UKCI 2012

ER -