This paper presents a novel approach for extracting high-quality <thread-title, reply> pairs as chat knowledge from online discussion forums so as to efficiently support the construction of a chatbot for a certain domain. Given a forum, the high-quality <thread-title, reply> pairs are extracted using a cascaded framework. First, the replies logically relevant to the thread title of the root message are extracted with an SVM classifier from all the replies, based on correlations such as structure and content. Then, the extracted <thread-title, reply> pairs are ranked with a ranking SVM based on their content qualities. Finally, the Top-N <thread-title, reply> pairs are selected as chatbot knowledge. Results from experiments conducted within a movie

“Before there were computers, we could distinguish persons from non-persons on the basis of an ability to participate in conversations. But now, we have hybrids operating between person and non persons with whom we can talk in ordinary language. ” (Colby 1999). Human machine conversation as a technology

In this report I present hierarchical parallel Markov models for the creation of interactive social agents for video games and entertainment. The approach extends existing, popular character technologies for social, communicative interaction. First, adding the knowledge of temporal interaction structure enables natural language interaction on a time scale much longer than current chatterbot technologies. Second, adding support for hierarchical interaction decomposition, where an interaction is represented as a collection of smaller, simpler elements, simplifies the authoring of complex engagement. Third, adding support for the concurrent engagement of these elements enables engagement in interleaved, naturalistic communication. The resulting decomposition supports redundancy of representation, graceful performance degradation through the simultaneous engagement of behaviors on different levels of abstraction, and the stochastic approximation mechanism increases robustness in the face of noise and ambiguity. In this report, I present the details of hierarchical parallel Markov models, I examine two entertainment agents that use this technique, and explain the implementational details of how such an approach can be used in the development of future systems.

This study concentrates on the dynamic interplay of affect and cognition in school mathematics learning. The aim of the study is to produce a systematic analysis and rich theoretical description of the functioning of affect and cognition in socio-culturally and contextually conditioned mathematics learning situations. The analysis and dynamic description are presented in close connection with the obtained research results of mathematics education and affect. The included meta-analysis or theoretical synthesis of previous research results is developed with respect to important recent conceptualizations of metacognition, self-regulation, and self-systems and to learning models applied in the scientific field of general educational psychology or within the psychological research of mathematics education. Various conceptualizations and models of affect, learning, and self-regulation are integrated in the study into a unified understanding of personal learning processes with affect and mathematics. The basic idea of the study consists of an emphasis laid on dynamic theoretical analyses and illustrations dealing with affect and mathematics learning or performances in the

Introduction Empirical and theoretical investigations of the nature and structure of human dialogue have been a topic of research in artificial intelligence and the more human areas of linguistics for decades: there has been much interesting work but no definitive or uncontroversial findings. the best performance overall has probably been Colby's PARRY (Colby,1973) since its release on the (then ARPA) net around 1973. It was robust, never broke down, always had something to say and, because it was intended to model paranoid behaviour, its zanier misunderstandings could always be taken as further evidence of mental disturbance rather than the processing failures they were. Colby actually carried out a version of the Turing test (Turing,1950) by getting psychiatrists to compare blind PARRY utterances with those of real paranoids and they were unable to distinguish them---indistinguishability results are never statistically watertight, but it was, nonetheless, a very striking demonstrat

The candidate confirms that the work submitted is her own and that appropriate credit has been given where reference has been made to the work of others. This copy is supplied on the understanding that it is copyright material and that no quotation from the thesis may be published without proper acknowledgementFor my father, David Jorge Schiffrin, Caminante, son tus huellas El camino y nada más; Caminante, no hay camino, Se hace camino al andar. Traveller, your footprints Are the road and nothing else; Traveller, there is no road, You make the road by walking. Al andar se hace camino Y al volver la vista atrás Se ve la senda que nunca