Generating Japanese Text from Conceptual Representation
Most methods for machine generation of Japanese sentences work from intermediary representations in syntactic structures, or tree structures, especially in machine translation systems. As the first Japanese text generation program to work directly from conceptual representations, our system represents a major departure from the approach. These conceptual representations include no explicit syntactic information. Rather, the representation contains scenes that correspond to events, including input on actors, objects, time, location and relations to other events. The generator builds complete Japanese sentence structure from the representation, and then refines it.
Unable to display preview. Download preview PDF.
- [Lytinen and Schank 82]Lytinen, Steve L. and Schank, Roger C. Representation and Translation. Research Report #234, Dept. of Computer Science, Yale Univ., 1982.Google Scholar
- [Schank 75]
- [Schank 80]Schank, Roger C. Language and Memory. Cognitive Science, Vol.4 No.3, 1980.Google Scholar
- [Tanaka, et al. 81]Tanaka, Hozumi et al. Natural Language Processing and Linguistics. Circulars of the Electrotechnical Lab. No.205, 1981.Google Scholar
- [Lebowitz 80]Lebowitz, Michael Generalization and Memory in an Integrated Understanding System. Research Report #186, Dept. of Computer Science, Yale Univ., 1980.Google Scholar
- [McGuire]McGuire, Rod Programs for Generation on DEC 20. Dept. of Computer Science, Yale Univ.Google Scholar
- [McDonald 83]McDonald, David D. Natural Language Generation Problem: An Introduction to Computational Models of Discourse. M. Brady and R. C. Berwick ed., MIT Press.Google Scholar
- [Ishizaki 83]Ishizaki, Shun and Isahara, Hitoshi On Japanese Text Generation from Conceptual Representation by Using Embedded Structure. Natural Language Processing Technology Symposium Information Processing Society, June 1983.Google Scholar
- [Ishizaki 83]Ishizaki, Shun Generation of Japanese Sentences from Conceptual Representation. IJCAI’83, August 1983.Google Scholar