I have worked with several substance-misusing clients who, despite my best efforts, adamantly adhere to their problematic narrative and cannot participate in re-storying their experience in a meaningful manner. The purpose of this article is to outline an alternative technique of using films to help substance-misusing clients generate a positive metaphor for their lived experiences. Using this ...

Spoken language dialogue is a comfortable form of communication between humans and computers, which is present in a growing number of commercial systems. For each task which can be comfortably performed in spoken language dialogue with the computer, there is an equivalence class of tasks which can be performed using similar dialogue management technology. Each such task class has a number of mi...

According to the author's narrative model of change, clients may maintain a problematic self-stability across therapy, leading to therapeutic failure, by a mutual in-feeding process, which involves a cyclical movement between two opposing parts of the self. During innovative moments (IMs) in the therapy dialogue, clients' dominant self-narrative is interrupted by exceptions to that self-narrati...

This paper describes a component based-model for a Narrative Conversational Agent. This project has to interact with a child in a storytelling environment as natural as possible and replace the previous version of the platform, where the actions were triggered manually by a psychologist. The prototype was carried out as a student project, and had the goal to integrate existing components and li...

Abstract This work shows how interaction is essential for storytelling with a child. A corpus of narrative dialogues between parents and their children was coded with a mentalist grid. The results of two modelling methods were analysed by an expert in parent-child dialogue analysis. The extraction of dialogue patterns reveals regularities explaining the character’s emotion. Results showed that ...

Unsupervised machine learning approaches hold great promise for recognizing dialogue acts, but the performance of these models tends to be much lower than the accuracies reached by supervised models. However, some dialogues, such as task-oriented dialogues with parallel task streams, hold rich information that has not yet been leveraged within unsupervised dialogue act models. This paper invest...

In dialogue, language processing is adapted to the conversational partner. We hypothesize that the brain facilitates partner-adapted language processing through preparatory neural configurations (task sets) that are tailored to the conversational partner. In this experiment, we measured neural activity with functional magnetic resonance imaging (fMRI) while healthy participants in the scanner (...