Effects of the user model on simulation-based learning of dialogue strategies

Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular, the degree to which strategies learned with a user model generalise to real user populations has not be investigated. This paper presents a series of experiments that qualitatively and quantitatively examine the effect of the user model on the learned strategy. Our results show that the performance and characteristics of the strategy are in fact highly dependent on the user model. Furthermore, a policy trained with a poor user model may appear to perform well when tested with the same model, but fail when tested with a more sophisticated user model. This raises significant doubts about the current practice of learning and evaluating strategies with the same user model. The paper further investigates a new technique for testing and comparing strategies directly on real human-machine dialogues, thereby avoiding any evaluation bias introduced by the user model. © 2005 IEEE.

Strategies for product recovery decisions

Product recovery is beset by uncertainty regarding the quality of end-of-life (EOL) products, and in order to ascertain the reusability of these products, they have to undergo expensive tests. This undermines the profitability of the recovery process. The key to improve the effectiveness of product recovery is to improve the quality of information available before testing. Emerging data capture technologies can significantly improve the availability of information. However, in order to maximise the potential of these technologies, appropriate decision-making algorithms that exploit such information must be developed. We model the recovery process using a decision-theoretic approach, and derive strategies to ascertain the reusability of EOL products, and also to decide when tests are beneficial. We show that improving the quality of information leads to increase in effectiveness of the recovery process by reducing the need for tests. Copyright © 2009 Inderscience Enterprises Ltd.

Statistics anxiety, trait anxiety, learning behavior, and academic performance

The present study investigated the relationship between statistics anxiety, individual characteristics (e.g., trait anxiety and learning strategies), and academic performance. Students enrolled in a statistics course in psychology (N=147) filled in a questionnaire on statistics anxiety, trait anxiety, interest in statistics, mathematical selfconcept, learning strategies, and procrastination. Additionally, their performance in the examination was recorded. The structural equation model showed that statistics anxiety held a crucial role as the strongest direct predictor of performance. Students with higher statistics anxiety achieved less in the examination and showed higher procrastination scores. Statistics anxiety was related indirectly to spending less effort and time on learning. Trait anxiety was related positively to statistics anxiety and, counterintuitively, to academic performance. This result can be explained by the heterogeneity of the measure of trait anxiety. The part of trait anxiety that is unrelated to the specific part of statistics anxiety correlated positively with performance.