Issue No. 04 - July/August (2009 vol. 24)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2009.79
Marjorie McShane , University of Maryland Baltimore County
This paper presents a vision of how language-endowed, next-generation intelligent agents might resolve—that is, fully interpret—references to objects and events in language input. It describes some of the more difficult reference phenomena that are not being sufficiently treated by practical systems and suggests what kinds of knowledge must be available to intelligent agents to enable them to reach human competence in reference resolution.
linguistics, natural language, ieee intelligent systems, human-level intelligence, ai
M. McShane, "Reference Resolution Challenges for Intelligent Agents: The Need for Knowledge," in IEEE Intelligent Systems, vol. 24, no. , pp. 47-58, 2009.