Evaluating the portability of revision rules for incremental summary generation

Authors:
Jacques Robin
Affiliations:
Universidade Federal de Pernambuco, Cidade Universitária, Recife, Brazil
Venue:
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Year:
1996

Citing 4
Cited 0

Expressing rhetorical relations in instructional text: a case study of the purpose relation

Computational Linguistics
Revision-based generation of natural language summaries providing historical background: corpus-based analysis, design, implementation and evaluation

Revision-based generation of natural language summaries providing historical background: corpus-based analysis, design, implementation and evaluation
Generating natural language explanations from large-scale knowledge bases

Generating natural language explanations from large-scale knowledge bases
Empirically designing and evaluating a new revision-based model for summary generation

Artificial Intelligence - Special volume on empirical methods

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a quantitative evaluation of the portability to the stock market domain of the revision rule hierarchy used by the system STREAK to incrementally generate newswire sports summaries. The evaluation consists of searching a test corpus of stock market reports for sentence pairs whose (semantic and syntactic) structures respectively match the triggering condition and application result of each revision rule. The results show that at least 59% of all rule classes are fully portable, with at least another 7% partially portable.