Working with clinicians to improve a patient-information NLG system

Authors:
Saad Mahamood;Ehud Reiter
Affiliations:
University of Aberdeen, Scotland, United Kingdom;University of Aberdeen, Scotland, United Kingdom
Venue:
INLG '12 Proceedings of the Seventh International Natural Language Generation Conference
Year:
2012

Citing 6
Cited 0

Agile Software Development: Principles, Patterns, and Practices

Agile Software Development: Principles, Patterns, and Practices
User Centered System Design; New Perspectives on Human-Computer Interaction

User Centered System Design; New Perspectives on Human-Computer Interaction
Automatic generation of textual summaries from neonatal intensive care data

Artificial Intelligence
From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management

AI Communications
Acquiring correct knowledge for natural language generation

Journal of Artificial Intelligence Research
Generating affective natural language for parents of neonatal infants

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation

Quantified Score

Hi-index	0.00

Visualization

Abstract

NLG developers must work closely with domain experts in order to build good NLG systems, but relatively little has been published about this process. In this paper, we describe how NLG developers worked with clinicians (nurses) to improve an NLG system which generates information for parents of babies in a neonatal intensive care unit, using a structured revision process. We believe that such a process can significantly enhance the quality of many NLG systems, in medicine and elsewhere.