![](bg8.png)
the English word ‘which’ is replaced here with the
Spanish word ‘que’.
JO8: If SS A is ‘Juan come manzanas’ and SS B is
‘María compra manzanas’, the combined sentence is
‘Juan come manzanas compradas por María’.
JO9: If SS A is ‘Juan está viendo la televisión’ and
SS B is ‘Ver la televisión es divertido’, the
combined sentence is ‘Juan está viendo la televisión.
Ver la televisión es divertido’.
JO10: If SS A is ‘Juan compra manzanas’ and SS B
is ‘María compra plátanos’, the combined sentence
is ‘Ellos compran fruta’.
It is our belief that this procedure can also be applied
to other European languages such as French or
Italian.
5 CONCLUSIONS AND FUTURE
WORK
Interactive Genetic Programming can be used in
generating dialogues for conversational agents. Two
different approaches have been reviewed. The first
approach based on the use of grammars, and the
second approach based on the use of Sentence Plan
Trees (SPTs).
Both approaches present the advantage of
providing answers adapted to each user thanks to the
evolutionary process, instead of giving predefined
static answers.
The use of SPTs as representation format is
recommended given that the use of grammars is
domain-specific, more complex for the designer of
the conversational agent, and it requires more time
to reach good answers.
Furthermore, as future work it is advisable to
permit users to start the dialogue, to find out the
satisfaction degree of the users by their answers, and
extending the procedure to other languages.
ACKNOWLEDGEMENTS
This work has been sponsored by the project
CCG08-UAM/TIC-4425.
REFERENCES
Araujo, L., 2004. Symbiosis of evolutionary techniques
and statistical natural language processing. IEEE
Transactions on Evolutionary Computing 8(1),14–27.
Araujo, L. 2007. How evolutionary algorithms are applied
to statistical natural language processing, Artificial
Intelligence Review 28, 275-303.
Goldberg, D.E., 1989. Genetic algorithms in search,
optimization and machine learning. Addison Wesley.
Hervás, R., Gervás, P., 2005. Applying genetic algorithms
to referring expression generation. In: Tenth
international conference on computer aided systems
theory, EUROCAST.
Holland, J.J., 1975. Adaptation in natural and artificial
systems. University of Michigan Press, Ann Arbor.
Karamanis, N., Manurung, H.M., 2002. Stochastic text
structuring using the principle of continuity. In:
Proceedings of the second international natural
language generation conference, Association for
Computational Linguistics, Harriman, NY, 81-88.
Kim, K., Lim, S., Cho, S., 2004. User Adaptive Answers
Generation for conversational Agent Using Genetic
Programming, in Z.R. Yang et al., ed. Intelligent Data
Engineering and Automated Learning, Lecture Notes
in Computer Science 3177, Springer-Verlag, 813-819.
Koza, J., 1994. Genetic programming, Automatic
discovery of reusable programs, the MIT Press.
Lester, J., Brandy, K., Mott, B., 2004. The Practical
Handbook of Internet Computing, Chapman & Hall,
chapter Conversational Agents, 220-241.
Lim, S., Cho, S., 2005. Language Generation for
Conversational Agent by Evolution of Plan Trees with
Genetic Programming, in V. Torra et al., ed., Modeling
Decisions for Artificial Intelligence, Lecture Notes in
Artificial Intelligence 3558, Springer-Verlag, 305-315.
Macskassy, S., Stevenson, S., 1996. A conversational
agent, Master Essay, Rutgers University, 1996.
McKeown, K., 1986. Language generation: Applications,
issues, and approaches, IEEE Proceedings 74(7),
905-919.
Michalewicz, Z., 1994. Genetic algorithms + data
structures = evolution programs, 2nd ed. Springer,
New York.
Oh, H., Rudnicky, I., 2002. Stochastic natural language
generation for spoken dialog systems, Computer
Speech and Language, 16(3-4), 387-407.
Ratnaparkhi, A., 2002. Trainable approaches to surface
natural language generation and their application to
conversational dialog systems, Computer Speech and
Language, 16(3-4), 435-455.
Takagi, H., 2001. Interactive evolutionary computation:
Fusion of the capabilities of EC optimization and
human evaluation, IEEE Proceedings, 89(9), 1275-
1296.
Weizenbaum, J., 1966. Eliza -a computer program for the
study of natural language communication between
man and machine, Communications of the ACM, 9, 26-
45.
ICAART 2010 - 2nd International Conference on Agents and Artificial Intelligence
366