Abstract
In this paper we address the problem of redundancy in text generation. Redundancy typically occurs when the material selected for communication contains information that is duplicated in the text, or else is so closely related that the reader can automatically infer one piece when reading another. Such redundant material is invariably removed by people, and ought to be removed by generator systems, to produce better quality text. We call the process of removing redundancy aggregation. In addressing the problem, three questions arise: Why do people object to redundancy? Which redundant portions are best removed? What mechanisms or rules are used to remove redundant information? In this paper we begin to answer the third question by identifying and describing the aggregation processes generators can use. We first survey the studies we have found on aspects of aggregation. We next outline a study we performed with human subjects. Finally, we define and describe eight aggregation strategies we identified, and discuss several associated issues and open questions.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
Dalianis, H. (1992a). A method for validating a conceptual model by natural language discourse generation. In CAISE-92 International Conference on Advanced Information Systems Engineering, Loucopoulos P. (ed.). Springer Verlag Lecture Notes in Computer Science no. 593 (425–444).
Dalianis, H. (1992b). A natural language generation system for validating specifictions for telephone services. Technical report, Ellemtel Telecom Labs, älvsjö, Sweden, and The Royal Institute of Technology, Stockholm University.
Dale, R. (1990). Generating Recipes: An Overview of Epicure. In Current Research in Natural Language Generation, R. Dale et al. (eds.). Academic Press Limited (229–255).
Echarti, J-P. and Stålmarck, G. (1988). A logical framework for specifying discrete dynamic systems. Technical report, Ellemtel Telecom Labs, älvsjö, Sweden.
Echarti, J-P. and Stålmarck, G. (1989). Towards a logical framework for modelling and validating the behaviour of telecommunication services. Technical report, Ellemtel Telecom Labs, älvsjö, Sweden.
Engstedt, M. (1991). A fFexible Specification Language Using Natural Language and Graphics. Master's Thesis. The Centre of Cognive Science, University of Edinburgh.
Engstedt, M. and Preifelt, S. (1992a). Results from the user tests of VINST. Technical report EUA F92 0864, Ellemtel Telecom labs, älvsjö, Sweden.
Engstedt, M. and Preifelt, S. (1992b). A System Description of the VINST prototype. Technical report EUA F92 22 75, Ellemtel Telecom Labs, älvsjö, Sweden.
Grice, H.P. (1975). Logic and Conversation. In Syntax and Semantics 3, Speech Acts, Cole, P. and Morgan, J.L. (eds.). New York: Academic Press (41–58).
Horacek, H. (1992). An integrated view of text planning. In Aspects of Automated Natural Language Generation, R. Dale et al. (eds.). Springer Verlag Lecture Notes in Artifical Intelligence no. 587 (193–227).
Hovy, E.H. (1988). Generating Natural Language under Pragmatic Constraints. Hillsdale, New Jersey: Lawrence Erlbaum Associates Publishers.
Hovy, E.H. (1990). Unresolved issues in paragraph planning. In Current Research in Natural Language Generation, R. Dale et al. (eds.). Academic Press Limited (17–45).
Hovy, E.H. (1992). Sentence Planning requirements for automated explanation generation. In Proceedings of the Workshop on Explanation Facilities for Model-Based Expert Systems, DIAMOD-Bericht no. 23. GMD St. Augustin, Germany.
Kempen, G. (1991). Conjunction reduction and gapping in clause-level coordination: An inheritance-based approach. Computational Intelligence 7 (4) (357–360).
Mann, W.C. and Moore, J.A. (1980). Computer as Author — Results and Prospects. Research Report ISI/RR-79-82, University of Southern California Information Sciences Institute, Marina del Rey.
Mann, W.C and Thompson, S.A. (1988). Rhetorical Structure Theory: Towards a Functional Theory of Text Organization. TEXT 8 (3) (243–281).
Rambow, O. (1990). Domain Communication Knowledge. In Proceedings of the 5th International Workshop on Generation. Pittsburgh, PA (87–95).
Scott, D. and de Souza, C.S. (1990). Getting the Message Across in RST-based Text Generation. In Current Research in Natural Language Generation, R. Dale et al. (eds.). Academic Press Limited (47–73).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dalianis, H., Hovy, E. (1996). Aggregation in natural language generation. In: Adorni, G., Zock, M. (eds) Trends in Natural Language Generation An Artificial Intelligence Perspective. EWNLG 1993. Lecture Notes in Computer Science, vol 1036. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60800-1_25
Download citation
DOI: https://doi.org/10.1007/3-540-60800-1_25
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60800-4
Online ISBN: 978-3-540-49457-7
eBook Packages: Springer Book Archive