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.
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 language | English |
---|---|
Title of host publication | Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI) |
Publisher | IEEE Explore |
Number of pages | 6 |
ISBN (Electronic) | 978-1-4244-8775-2, 978-1-4244-8773-8 |
ISBN (Print) | 978-1-4244-8774-5 |
DOIs | |
Publication status | Published - 2010 |
Event | Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI) - Essex, United Kingdom Duration: 8 Sep 2010 → 10 Sep 2010 |
Publication series
Name | UK Workshop on Computational Intelligence (UKCI) |
---|---|
Publisher | IEEE |
ISSN (Print) | 2162-7657 |
Conference
Conference | Proceedings of the 10th UK Workshop on Computational Intelligence (UKCI) |
---|---|
Country/Territory | United Kingdom |
City | Essex |
Period | 8/09/10 → 10/09/10 |