In Logic and Ontology Cocchiarella (2001) convincingly argues for a view of "logic as a language" in contrast with the (now dominant) view of "logic as a calculus". In the latter, logic is viewed as an "abstract calculus that has no content of its own, and which depends on set theory as a background framework by which such a calculus might be syntactically described and semantically interpreted." In the view of "logic as a language", however, logic has content, and "ontological content in particular." Moreover, and according to Cocchiarella, a logic with ontological content necessitates the use of type theory (and predication), as opposed to set theory (and set membership), as the background framework. An obvious question that immediately comes to mind here is the following: what exactly is the nature of this strongly-typed ontological structure that will form the background framework for a new logic that has content?

In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like ``after", which overtly signal a temporal relation. We first show that models trained on main and subordinate clauses connected with a temporal marker achieve good performance on a pseudo-disambiguation task simulating temporal inference (during testing the temporal marker is treated as unseen and the models must select the right marker from a set of possible candidates). Secondly, we assess whether the proposed approach holds promise for the semi-automatic creation of temporal annotations. Specifically, we use a model trained on noisy and approximate data (i.e., main and subordinate clauses) to predict intra-sentential relations present in TimeBank, a corpus annotated rich temporal information. Our experiments compare and contrast several probabilistic models differing in their feature space, linguistic assumptions and data requirements. We evaluate performance against gold standard corpora and also against human subjects.

Multimodal conversational interfaces provide a natural means for users to communicate with computer systems through multiple modalities such as speech and gesture. To build effective multimodal interfaces, automated interpretation of user multimodal inputs is important. Inspired by the previous investigation on cognitive status in multimodal human machine interaction, we have developed a greedy algorithm for interpreting user referring expressions (i.e., multimodal reference resolution). This algorithm incorporates the cognitive principles of Conversational Implicature and Givenness Hierarchy and applies constraints from various sources (e.g., temporal, semantic, and contextual) to resolve references. Our empirical results have shown the advantage of this algorithm in efficiently resolving a variety of user references. Because of its simplicity and generality, this approach has the potential to improve the robustness of multimodal input interpretation.

We present a novel framework for integrating prior knowledge into discriminative classifiers. Our framework allows discriminative classifiers such as Support Vector Machines (SVMs) to utilize prior knowledge specified in the generative setting. The dual objective of fitting the data and respecting prior knowledge is formulated as a bilevel program, which is solved (approximately) via iterative application of second-order cone programming. To test our approach, we consider the problem of using WordNet (a semantic database of English language) to improve low-sample classification accuracy of newsgroup categorization. WordNet is viewed as an approximate, but readily available source of background knowledge, and our framework is capable of utilizing it in a flexible way.

We develop a novel algorithm, called VIP*, for structured variational approximate inference. This algorithm extends known algorithms to allow efficient multiple potential updates for overlapping clusters, and overcomes the difficulties imposed by deterministic constraints. The algorithm's convergence is proven and its applicability demonstrated for genetic linkage analysis.

Modeling Decision for Artificial Intelligence (MDAI 2006)

Dynamic scripting is a reinforcement learning approach to adaptive game AI that learns, during gameplay, which game tactics an opponent should select to play effectively. We introduce the evolutionary state-based tactics generator (ESTG), which uses an evolutionary algorithm to generate tactics automatically. Experimental results show that ESTG improves dynamic scripting's performance in a real-time strategy game. We conclude that high-quality domain knowledge can be automatically generated for strong adaptive game AI opponents.

This editorial introduces the articles published in the AI Magazine special issue on Innovative Applications of Artificial Intelligence (IAAI), based on a selection of papers that appeared in the IAAI-05 conference, which occurred July 9-13 2005 in Pittsburgh, Pennsylvania. IAAI is the premier venue for learning about AI's impact through deployed applications and emerging AI application technologies. The emerging applications track features technologies that are rapidly maturing to the point of application. Three articles from the emerging technology track were particularly innovative and demonstrated some unique technology features ripe for deployment.

Modeling Decision for Artificial Intelligence (MDAI 2006) Abstract In this document we report on the MDAI 2006 conference that was held in Tarragona (Catalonia, Spain) in April 2006. In this document we report on the MDAI 2006 conference that was held in Tarragona (Catalonia, Spain) in April 2006.

This article describes the ExpertCop tutorial system, a simulator of crime in an urban region. In ExpertCop, the students (police officers) configure and allocate an available police force according to a selected geographic region and then interact with the simulation. The student interprets the results with the help of an intelligent tutor, the pedagogical agent, observing how crime behaves in the presence of the allocated preventive policing. The pedagogical agent implements interaction strategies between the student and the geosimulator, designed to make simulated phenomena better understood.