The importance of narrative and other lessons from an evaluation of an NLG system that summarises clinical data

Authors:
Ehud Reiter;Albert Gatt;François Portet;Marian van der Meulen
Affiliations:
University of Aberdeen, UK;University of Aberdeen, UK;University of Aberdeen, UK;University of Edinburgh, UK
Venue:
INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
Year:
2008

Citing 10
Cited 7

Temporal ontology and temporal reference

Computational Linguistics - Special issue on tense and aspect
Using Natural-Language Processing to Produce Weather Forecasts

IEEE Expert: Intelligent Systems and Their Applications
Narrative prose generation

Artificial Intelligence
Document structure

Computational Linguistics
Preventing false temporal implicatures: interactive defaults for text generation

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Choosing the content of textual summaries of large time-series data sets

Natural Language Engineering
An architecture for data-to-text systems

ENLG '07 Proceedings of the Eleventh European Workshop on Natural Language Generation
Choosing words in computer-generated weather forecasts

Artificial Intelligence - Special volume on connecting language to the world
Generating and evaluating evaluative arguments

Artificial Intelligence
Using spatial reference frames to generate grounded textual summaries of georeferenced data

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference

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

AI Communications
Using NLG to help language-impaired users tell stories and participate in social dialogues

ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
Textual properties and task based evaluation: investigating the role of surface properties, structure and content

INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Automatically generating stories from sensor data

Proceedings of the 16th international conference on Intelligent user interfaces
Generating automated news to explain the meaning of sensor data

IDA'11 Proceedings of the 10th international conference on Advances in intelligent data analysis X
Trap hunting: finding personal data management issues in next generation AAC devices

SLPAT '11 Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies
What is in a text and what does it do: qualitative evaluations of an NLG system -- the BT-Nurse -- using content analysis and discourse analysis

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

The BABYTALK BT-45 system generates textual summaries of clinical data about babies in a neonatal intensive care unit. A recent task-based evaluation of the system suggested that these summaries are useful, but not as effective as they could be. In this paper we present a qualitative analysis of problems that the evaluation highlighted in BT-45 texts. Many of these problems are due to the fact that BT-45 does not generate good narrative texts; this is a topic which has not previously received much attention from the NLG research community, but seems to be quite important for creating good data-to-text systems.