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
Date
2011-09Author
Sambaraju, Rahul
Reiter, E.
Logie, R.
McKinlay, A.
McVittie, Chris
Gatt, A.
Sykes, C.
Metadata
Show full item recordCitation
Sambaraju, R., Reiter, E., Logie, R., McKinlay, A., McVittie, C., Gatt, A. & Sykes, C. (2011) 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 2011 - 13th European Workshop on Natural Language Generation, Proceedings, , , pp. 22-31,
Abstract
Evaluations of NLG systems generally are quantiative, that is, based on corpus comparison statistics and/or results of experiments with people. Outcomes of such evaluations are important in demonstrating whether or not an NLG system is successful, but leave gaps in understanding why this is the case. Alternatively, qualitative evaluations carried out by experts provide knowledge on where a system needs to be improved. In this paper we describe two such evaluations carried out for the BT-Nurse system, using two different methodologies (content analysis and discourse analysis). The outcomes of such evaluations are discussed in comparison to what was learnt from a quantitiave evaluation of BT-Nurse. Implications for the role of similar evaluations in NLG are also discussed. 2011 Association for Computational Linguistics.