Abstract
This paper presents the first quantitative, corpus-based evaluation of the same-domain robustness and scalability of a new revision-based language generation model, in comparison to the traditional single pass pipeline model. Robustness is defined as the proportion of sentences, in a given corpus test sample that can be generated using only knowledge structures abstracted from another sample. Scalability is defined as the proportion of knowledge structures, among those needed to generate all sentences from a given corpus test sample, of those already acquired from another sample. Results show that the incremental revision model is far more robust and significantly more scalable than the single pass model.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
L. Bourbeau, D. Carcagno, E. Goldberg, R. Kittredge, and A. Polguère. Bilingual generation of weather forecasts in an operations environment. In Proceedings of the 13th International Conference on Computational Linguistics, Helsinki University, Finland, 1990. COLING.
D. Duford. Crep: a regular expression-matching textual corpus tool. Technical Report CUCS-005-93, Columbia University, 1993.
K. Kukich. Knowledge-based report generation: a knowledge engineering approach to natural language report generation. PhD thesis, University of Pittsburgh, 1983.
J.C. Lester. Generating natural language explanations from large-scale knowledge bases. PhD thesis, Computer Science Department, Universtity of Texas at Austin, New York, NY, 1994.
J. Robin. A revision-based generation architecture for reporting facts in their historical context. In H. Horacek and M. Zock, editors, New Concepts in Natural Language Generation: Planning, Realization and Systems. Frances Pinter, London and New York, 1993.
J. Robin. Automatic generation and revision of natural language summaries providing historical background. In Proceedings of the 11th Brazilian Symposium on Artificial Intelligence, Fortaleza, CE, October 1994.
J. Robin. Evaluating the portability of revision rules for incremental summary generation. In Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics, Santa Cruz, California, 1996. ACL.
J. Robin and K. McKeown. Corpus analysis for revision-based generation of complex sentences. In Proceedings of the 11th National Conference on Artificial Intelligence, pages 365–372. AAAI, 1993.
K. Van der Linden and J.H. Martin. Expressing rhetorical relations in instructional texts: a case study of the purpose relation. Computational Linguistics, 21(1):29–58, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Robin, J. (1996). Evaluating the robustness and scalability of revision-based natural language generation. In: Borges, D.L., Kaestner, C.A.A. (eds) Advances in Artificial Intelligence. SBIA 1996. Lecture Notes in Computer Science, vol 1159. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61859-7_12
Download citation
DOI: https://doi.org/10.1007/3-540-61859-7_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61859-1
Online ISBN: 978-3-540-70742-4
eBook Packages: Springer Book Archive