ThisvolumecontainsthepaperspresentedatAI 2008, the 21stconferenceofthe CanadianSociety for the Computational Study of Intelligence (CSCSI). AI 2008 attracted 75 paper submissions. Each paper was assigned to four reviewers. One goalfor AI2008wasto re?ecta widerangeofdi?erent research, thusin addition to regular papers, these proceedings also include short papers of researchthat is still in its early stages. The Program Committee selected 30 regular papers and 5 short papers for publication. AI 2008 was a collaboration of many people. Most importantly, my thanks go to the members of the Program Committee and the additional reviewers, who provided high-quality reviews, making the task of selecting from a wide variety of papers possible. I also bene?ted greatly from the patient advice from the previous Program Chairs and current Local Arrangements Chairs Dan Wu and Ziad Kobti, as well as the General Conference Chair, Howard Hamilton. The EasyChair conference management system by Andrei Voronkov once again lived up to its name. Final thanks go to the CSCSI Executive Committee, and especially Danny Silver, for their support and for making AI 2008 a successful conference. May 2008 Sabine Bergler Organization AI 2008 was organized by the Canadian Society for the Computational Study of Intelligence (CSCSI

Recent work on formal methods in computational lexical semantics has had theeffect of bringing many linguistic formalisms much closer to the knowledge representation languages used in artificial intelligence. Formalisms are now emerging which may be more expressive and formally better understood than many knowledge representation languages. The interests of computational linguists now extend to include such domains as commonsense knowledge, inheritance, default reasoning, collocational relations, and even domain knowledge. With such an extension of the normal purview of "linguistic" knowledge, one may question whether there is any logical justification for distinguishing between lexical semantics and commonsense reasoning. This volume explores the question from several methodologicaland theoretical perspectives. What emerges is a clear consensus that the notion of the lexicon and lexical knowledge assumed in earlier linguistic research is grossly inadequate and fails to address the deeper semantic issues required for natural language analysis.