Moving from data to text using causal statements in explanatory narratives

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

1 Citation (Scopus)

Abstract

Data-to-text natural language generation techniques
do not currently impart deep meaning in their output
and leave it to an expert user to draw causal inferences.
Frequently, the expert is adding meaning that would be present
in data sources that could be made available to the NLG system.
As the system is intended to convey as much information as
possible, it seems counterintuitive to require the user to add
meaning that could already have been included in the systems
output. In this paper, we introduce our concept of using a
reasoning engine to draw causal inferences about the data and
then expressing them in an explanatory narrative.
Original languageEnglish
Title of host publicationProceedings of the 10th UK Workshop on Computational Intelligence (UKCI)
PublisherIEEE Explore
Number of pages6
Publication statusPublished - 2010
EventProceedings of the 10th UK Workshop on Computational Intelligence (UKCI) - Essex, United Kingdom
Duration: 8 Sep 201010 Sep 2010

Conference

ConferenceProceedings of the 10th UK Workshop on Computational Intelligence (UKCI)
CountryUnited Kingdom
CityEssex
Period8/09/1010/09/10

Fingerprint

Engines

Cite this

Matheson, D. E., Sripada, G. S., & Coghill, G. M. (2010). Moving from data to text using causal statements in explanatory narratives. In Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI) IEEE Explore.

Moving from data to text using causal statements in explanatory narratives. / Matheson, Donald Ewan; Sripada, Gowri Somayajulu; Coghill, George MacLeod.

Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI). IEEE Explore, 2010.

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

Matheson, DE, Sripada, GS & Coghill, GM 2010, Moving from data to text using causal statements in explanatory narratives. in Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI). IEEE Explore, Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI), Essex, United Kingdom, 8/09/10.
Matheson DE, Sripada GS, Coghill GM. Moving from data to text using causal statements in explanatory narratives. In Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI). IEEE Explore. 2010
Matheson, Donald Ewan ; Sripada, Gowri Somayajulu ; Coghill, George MacLeod. / Moving from data to text using causal statements in explanatory narratives. Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI). IEEE Explore, 2010.
@inproceedings{a2d5ad2524f444ddb577e2dd7792b533,
title = "Moving from data to text using causal statements in explanatory narratives",
abstract = "Data-to-text natural language generation techniques do not currently impart deep meaning in their output and leave it to an expert user to draw causal inferences. Frequently, the expert is adding meaning that would be present in data sources that could be made available to the NLG system. As the system is intended to convey as much information as possible, it seems counterintuitive to require the user to add meaning that could already have been included in the systems output. In this paper, we introduce our concept of using a reasoning engine to draw causal inferences about the data and then expressing them in an explanatory narrative.",
author = "Matheson, {Donald Ewan} and Sripada, {Gowri Somayajulu} and Coghill, {George MacLeod}",
year = "2010",
language = "English",
booktitle = "Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI)",
publisher = "IEEE Explore",

}

TY - GEN

T1 - Moving from data to text using causal statements in explanatory narratives

AU - Matheson, Donald Ewan

AU - Sripada, Gowri Somayajulu

AU - Coghill, George MacLeod

PY - 2010

Y1 - 2010

N2 - Data-to-text natural language generation techniques do not currently impart deep meaning in their output and leave it to an expert user to draw causal inferences. Frequently, the expert is adding meaning that would be present in data sources that could be made available to the NLG system. As the system is intended to convey as much information as possible, it seems counterintuitive to require the user to add meaning that could already have been included in the systems output. In this paper, we introduce our concept of using a reasoning engine to draw causal inferences about the data and then expressing them in an explanatory narrative.

AB - Data-to-text natural language generation techniques do not currently impart deep meaning in their output and leave it to an expert user to draw causal inferences. Frequently, the expert is adding meaning that would be present in data sources that could be made available to the NLG system. As the system is intended to convey as much information as possible, it seems counterintuitive to require the user to add meaning that could already have been included in the systems output. In this paper, we introduce our concept of using a reasoning engine to draw causal inferences about the data and then expressing them in an explanatory narrative.

M3 - Conference contribution

BT - Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI)

PB - IEEE Explore

ER -