This paper shows that automatically generated questions can help classify children’s spoken responses to a reading tutor teaching them to generate their own questions. We use automatic question generation to model and classify children’s prompted spoken questions about stories. On distinguishing complete and incomplete questions from irrelevant speech and silence, a language model built from automatically generated questions out-performs a trigram language model that does not exploit the structure of questions.

This research aims to define a novel framework to employ engineering and mathematical models to study adaptive dynamics in heterarchial systems. This multi-profile descriptive platform and modeling approach is developed as a composite of conceptual behaviors and structural entity aspects of engineered complex adaptive systems (ECAS). While the US electric power system will be utilized for demonstration and validation, the framework has applicability to the general class of ECASs that are artificially created but highly interactive with natural and behavioral sciences. Conditioned on parameterization of the framework, a theorem will be presented to calibrate current structure and predict future dynamic behaviors of an ECAS. We analyze decentralized heterarchial ECASs to infer emergent behavior of the components, and evolution processes and adaptations of the whole system.

Learning to use an object as a tool requires understanding what goals it helps to achieve, the properties of the tool that make it useful and how the tool must be manipulated to achieve the goal. We present a method that allows a robot to learn about objects in this way and thereby employ them as tools. An initial hypothesis for an action model of tool use is created by observing another agent accomplishing a task using a tool. The robot then refines its hypothesis by active learning, generating new experiments and observing the outcomes. Hypotheses are updated using Inductive Logic Programming. One of the novel aspects of this work is the method used to select experiments so that the search through the hypothesis space is minimised.

Lane changing can increase or impede the flow of vehicular traffic, depending on traffic density and the lane-changing strategies used by individual drivers. We implement and extend the Nagel-Schreckenberg (N-S) traffic model as an agent-based model to investigate lane-changing behavior on a multi-lane roadway, with the goal of determining which lane changing strategies result in the greatest overall traffic flow. We show that in heavier traffic, an aggressive lane changing policy may be beneficial for overall traffic flow.

Next, through the Question Type Selection ArikIturri (Aldabe et al. 2006) is a system developed for the process, the question type is selected. Finally, by means automatic generation of different types of exercise. One of of the Question Construction step, the surface form of the the aims of ArikIturri is to generate items that could form question is created based on the previous steps. As regards part of real scenarios; this is why their creation is based our QG system, the sentence retriever module is responsible on topics that are part of the curriculum. Thus, the system for the Target Selection task and the item generator module is able to automatically generate tests from texts, to be included performs the Question Type Selection and Question Construction in testing tasks. The system is able to produce fill-inthe-blank processes.

The ability to delay intentions and remember them in the proper context is an important ability for general artificial agents. In this paper, we define the functional requirements of an agent capable of fulfilling delayed intentions with its long-term memories. We show that the long-term memories of different cognitive architec- tures share similar functional properties and that these mechanisms can be used to support delayed intentions. Finally, we do a preliminary evaluation of the different memories for fulfilling delayed intentions and show that there are trade-offs between memory types that warrant further research.

Recent studies on question generation identify the need for automatic discourse analysers. We evaluated the feasibility of integrating an available discourse analyser called HILDA for a specific question generation system called CODA; introduce an approach by extracting a discourse corpus from the CODA parallel corpus; and identified future work towards automatic discourse analysis in the domain of question generation.

We present a system capable of automatically solving combinatorial logic puzzles given in (simplified) English. It involves translating the English descriptions of the puzzles into answer set programming(ASP) and using ASP solvers to provide solutions of the puzzles. To translate the descriptions, we use a lambda-calculus based approach using Probabilistic Combinatorial Categorial Grammars (PCCG) where the meanings of words are associated with parameters to be able to distinguish between multiple meanings of the same word. Meaning of many words and the parameters are learned. The puzzles are represented in ASP using an ontology which is applicable to a large set of logic puzzles.

This paper argues the position that an essential approach to the advancement of the state of the art in cognitive systems is to focus on systems that deeply integrate knowledge representations, cognitive capabilities, and knowledge content. Integration is the path to aggregating constraints in ways that improve the science of cognitive systems. However, evaluating the role of knowledge among these constraints has largely been ignored, in part because it is difficult to build and evaluate systems that incorporate large amounts of knowledge. We provide suggestions for evaluating such systems and argue that such evaluations will become easier as we come closer to applying usefully new, integrated learning mechanisms that are capable of acquiring large and effective knowledge bases.

An important form of learning involves acquiring skills that let an agent achieve its goals. While there has been considerable work on learning in planning, most approaches have been sensitive to the representation of domain context, which hurts their generality. A learning mechanism that constructs skills effectively across different representations would suggest more robust behavior. In this paper, we present a novel approach to learning hierarchical task networks that acquires conceptual predicates as learning proceeds, making it less dependent on carefully crafted background knowledge. The representation acquisition procedure expands the system's knowledge about the world, and leads to more rapid learning. We show the effectiveness of the approach by comparing it with one that doesnot change domain representation.