Information Technology Reference
In-Depth Information
7
Conclusions and Future Work
We presented an approach for the automatic emulation of humanlike topic awareness
in ongoing small talk dialogs to extend the conversational abilities of a virtual agent
in human-agent interactions. More precisely, we proposed solutions for both tasks the
automatic identification of dialog topics and the integration of the resulting topic infor-
mation into the agent's existing system architecture. The several associated processes
fulfill the requirements given by a face-to-face encounter between a human and a con-
versational agent and enable both a coherent and socially adequate dialog between the
human and the artificial interlocutors. Thereby, we exploit Wikipedia knowledge and
hence the benefits originated from collaborative work (namely the existence of infor-
mation whose maintenance and expansion is carried out by numerous volunteers and
the reflection of the participants' common perception of conceptual structures).
In future, we will extend our approach by detecting and linking topical affiliations
to previous dialog topics to handle short
side trips
to past topics. Moreover, we will
resolve ambiguities by taking into account the current dialog topic to influence the
concept detection process.
Acknowledgements.
This work is kindly supported by the Deutsche Forschungsge-
meinschaft (DFG) in the context of the KnowCIT research project in the Center of Ex-
cellence Cognitive Interaction Technology (CITEC) at Bielefeld University. We thank
Birgit Endrass and Elisabeth Andre from the University of Augsburg for providing parts
of their CUBE-G corpus.
References
1. Breuing, A., Wachsmuth, I.: Let's talk topically with artificial agents! providing agents with
humanlike topic awareness in everyday dialog situations. In: Proceedings of the 4th Interna-
tional Conference on Agents and Artificial Intelligence (ICAART), pp. 62-71 (2012)
2. Svennevig, J.: Getting Acquainted in Conversation. John Benjamins Publishing (1999)
3. Clark, H.H.: Using Language. Cambridge Univ. Press (1996)
4. Endrass, B., Rehm, M., Andre, E.: Planning small talk behavior with cultural influences for
multiagent systems. Computer Speech and Language 25, 158-174 (2011)
5. Cassell, J., Bickmore, T., Campbell, L., Vilhjalmsson, H., Yan, H.: Human conversation as
a system framework: Designing embodied conversational agents. In: Cassell, J., Sullivan, J.,
Churchill, E. (eds.) Embodied Conversational Agents, pp. 29-63. MIT Press (2000)
6. Jurafsky, D., Martin, J.H.: Speech and Language Processing. Pearson Prentice Hall (2009)
7. Schank, R.C.: Rules and topics in conversation. Cognitive Science 1, 421-441 (1977)
8. Breuing, A., Waltinger, U., Wachsmuth, I.: Harvesting Wikipedia knowledge to identify top-
ics in ongoing natural language dialogs. In: Proceedings of the 2011 IEEE/WIC/ACM Inter-
national Joint Conference on Web Intelligence and Intelligent Agent Technology, pp. 445-
450. IEEE Press (2011)
9. Bublitz, W.: Topical coherence in spoken discourse. Studia Anglica Posnaniensia 22, 31-51
(1989)
10. Hobbs, J.: Topic drift. In: Dorval, B. (ed.) Conversational Organization and Its Development,
pp. 3-22. Ablex Publishing (1990)
11. Schneider, K.P.: Small Talk: Analysing Phatic Disourse. Hitzeroth (1988)
