Towards a possibility-theoretic approach to uncertainty in medical data interpretation for text generation

Authors:
François Portet;Albert Gatt
Affiliations:
Laboratoire d'Informatique de Grenoble, Grenoble Institute of Technology, France;Institute of Linguistics, University of Malta, Malta
Venue:
KR4HC'09 Proceedings of the 2009 AIME international conference on Knowledge Representation for Health-Care: data, Processes and Guidelines
Year:
2009

Citing 10
Cited 2

Temporal constraint networks

Artificial Intelligence - Special issue on knowledge representation
Maintaining knowledge about temporal intervals

Communications of the ACM
Testing the descriptive validity of possibility theory in human judgments of uncertainty

Artificial Intelligence - Special issue: Fuzzy set and possibility theory-based methods in artificial intelligence
Probabilistic Temporal Interval Networks

TIME '04 Proceedings of the 11th International Symposium on Temporal Representation and Reasoning
Fuzzy theory approach for temporal model-based diagnosis: An application to medical domains

Artificial Intelligence in Medicine
Temporal abstraction in intelligent clinical data analysis: A survey

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

AI Communications
Lexical choice of modal expressions

ENLG '07 Proceedings of the Eleventh European Workshop on Natural Language Generation
The algebra IAfuz: a framework for qualitative fuzzy temporal reasoning

Artificial Intelligence
Extending temporal databases to deal with telic/atelic medical data

AIME'05 Proceedings of the 10th conference on Artificial Intelligence in Medicine

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

AI Communications
If it may have happened before, it happened, but not necessarily before

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many real-world applications that reason about events obtained from raw data must deal with the problem of temporal uncertainty, which arises due to error or inaccuracy in data. Uncertainty also compromises reasoning where relationships between events need to be inferred. This paper discusses an approach to dealing with uncertainty in temporal and causal relations using Possibility Theory, focusing on a family of medical decision support systems that aim to generate textual summaries from raw patient data in a Neonatal Intensive Care Unit. We describe a framework to capture temporal uncertainty and to express it in generated texts by mean of linguistic modifiers. These modifiers have been chosen based on a human experiment testing the association between subjective certainty about a proposition and the participants' way of verbalising it.