Abstract
The task of natural language generation by computer requires a method for the selection of lexical items that refer to concepts. A generation system cannot assume that every concept will have an appropriate lexical entry associated with it. Similarly, a generation system must avoid redundant text and must strive for the most specific descriptions possible. This paper presents an algorithm for lexical selection that takes advantage of a conceptual network in which we represent the relationships between concepts (such as which concepts subsume each other and what differentiates concepts at different levels of generality). When the algorithm chooses a lexical realization for a concept, it first checks to see if the concept to be expressed is associated with a lexical entry. If so, that entry is used. If the concept does not have the appropriate lexical associations, the algorithm generates a phrase with a more general head term and restrictive modifiers. It does this by using the conceptual network to compute a semantically appropriate head term, and then modifying the request for generation by adding restrictions that differentiate the concept associated with the head term from the concept initially requested. Similarly, the conceptual network is used to eliminate redundant modifiers by computing the information contained in a lexical item that is chosen as a head term. Here the algorithm modifies the generation request to avoid restating the extra information. This algorithm is being implemented within Penman, a computerized system for the generation of English text from statements in a first-order predicate calculus language.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
AppeltDouglas E. 1985. Planning English Sentences. Cambridge: Cambridge University Press.
Brachman, R.J., and J.G. Schmolze. 1985. An Overview of the kl-one Knowledge Representation System. Cognitive Science. 171–216.
CarnapRudolph. 1956. Meaning and Necessity: A Study in Semantics and Modal Logic. Chicago: University of Chicago Press.
Cumming, Susanna. 1986. Design of a Master Lexicon. University of Southern California, Information Sciences Institute, Technical Report ISI/RR-85-163.
DanlosLaurence. 1985. Generation Automatique de Textes en Langues Naturelles. Paris: Masson.
DavidsonD. 1967. The Logical Form of Action Sentences. In: N.Rescher (Ed.), The Logic of Decision and Action. Pittsburgh: University of Pittsburgh Press, 81–95.
GoldmanN.M. 1975. Conceptual Generation. In: R.C.Schank (Ed.), Conceptual Information Processing. Amsterdam: North-Holland.
HallidayM.A.K. 1985. An Introduction to Functional Grammar. London: Edward Arnold.
HallidayM.A.K. 1976. System and Function in Language. London: Oxford University Press.
Hendrix, G. 1975. Expanding the Utility of Semantic Networks through Partioning. In: Advanced Papers of the Fourth International Joint Conference on Artificial Intelligence. Tbilisi, 115–121.
Hoeppner, Wolfgang, Thomas Christaller, Heinz Marburger, Katharina Morik, Bernhard Nebel, Mike O'Leary and Wolfgang Wahlster. 1983. Beyond Domain-Independence: Experience With the Development of a German Natural Language Access System to Highly Diverse Background Systems. Proceedings of IJCAI-83, Karlsruhe, 588–594.
HovyE. 1987. Generating Natural Language under Pragmatic Constraints. Journal of Pragmatics 11: 689–719.
JacobsPaul S. 1985a. phred: A Generator for Natural Language Interfaces. Computational Linguistics 11: 219–242.
Jacobs, Paul. 1985b. A Knowledge-Based Approach to Language Production, Ph.D. thesis. University of California, Berkeley.
Kaczmarek, T., W. Mark and N. Sondheimer. 1983. The Consul/CUE Interface: An Integrated Interactive Environment. In Proceedings of CHI '83, Human Factors in Computing Systems. ACM. 98–102.
Kaczmarek, T., R. Bates and G. Robins. 1986. Recent Developments in nikl. Proceedings of AAAI-86, Philadelphia, 978–985.
Kukich, Karen. 1983. Knowledge-Based Report Generation, Ph.D. thesis. University of Pittsburgh, Interdisciplinary Department of Information Science.
Mann, W.C. 1983a. An Overview of the Penman Text Generation System. In Proceedings of the National Conference on Artificial Intelligence, 261–265.
Mann, W.C. 1983b. Inquiry Semantics: A Functional Semantics of Natural Language Grammar. In Proceedings of the ACL, European Chapter.
Mann, William C., and Christian M.I.M. Matthiessen. 1983. Nigel: A Systemic Grammar for Text Generation. Information Sciences Institute, University of Southern California, Technical Report ISI/RR-83-105.
McAllester, D.A. 1982. Reasoning Utility Package User's Manual. MIT, Technical Report.
McDonald, David D. 1981. Language Production: The Source of the Dictionary. In Proceedings of ACL-81, Stanford, 57–62.
McDonald, David D. 1985. Description-Directed Natural Language Generation. In Proceedings of IJCAI-85, Los Angeles, 799–805.
McKeownKathleen R. 1985. Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge: Cambridge University Press.
MontagueR. 1974. Formal Philosophy. New Haven: Yale University Press.
Shapiro, S.C. 1979. Generalized Augmented Transition Network Grammars for Generation from Semantic Networks. In Proceedings of ACL-79, 25–29.
Sondheimer, Norman, and Bernhard Nebel. 1986. A Logical-Form and Knowledge-Base Design for Natural Language Generation. In Proceedings of AAAI-86, Philadelphia, 612–618.
Vilain, M. 1985. The Restricted Language Architecture of a Hybrid Representation System. In Proceedings of IJCAI-85, Los Angeles, 547–551.
Author information
Authors and Affiliations
Additional information
This research was done at the Information Sciences Institute, University of Southern California. It was supported by the Defense Advanced Research Projects Agency under Contract No. MDA903-81-C-0535 and by the Air Force Office of Scientific Research under Contract No. F49609620-87-C-0005. Views and conclusions contained in this report are the authors' and should not be interpreted as representing the official opinion or policy of darpa, afosr, the U.S. Government or any person or agency connected with them.
Rights and permissions
About this article
Cite this article
Sondheimer, N., Cumming, S. & Albano, R. How to realize a concept: Lexical selection and the conceptual network in text generation. Machine Translation 5, 57–78 (1990). https://doi.org/10.1007/BF00310042
Issue Date:
DOI: https://doi.org/10.1007/BF00310042