Data Set Used
Some computer game genres require meaningful stories and complex worlds in order to successfully engage players. In this paper we look at a procedural approach to story-based map generation focusing on the tight relationship between stories and the virtual worlds where those stories will unfold. Our long term goal is to develop procedural content generation… (More)
While most natural language understanding systems rely on a pipeline-based architecture, certain human text interpretation methods are based on a cyclic process between the whole text and its parts: the hermeneutic circle. In the task of automatically identifying characters and their narrative roles, we propose a feedback-loop-based approach where the… (More)
In this paper we propose a method for automatically assigning narrative roles to characters in stories. To achieve this goal our proposal is to combine natural language processing techniques with domain knowledge extracted from Propp's morphology of the folktale.
This paper presents an approach for automatically identifying high-level narrative structure information, particularly character roles, from unannotated folk tales. We introduce a new representation called action matrices to encode Propp's narrative theory on character role and their " sphere of action. " We tested our approach in a fully automated system… (More)
We present the preliminary work in the TAEMILE project, which aims to co-regulate the learning process in educational games by automatically balancing learners autonomy and the pedagogical processes intended by educators. We focus on our design rationale and the initial results from our user study.
We present a case-based approach to character identification in natural language text in the context of our Voz system. Voz first extracts entities from the text, and for each one of them, computes a feature-vector using both linguistic information and external knowledge. We propose a new similarity measure called Continuous Jac-card that exploits those… (More)
Little Newton is a 3D defense game in which the player learns about basic physics concepts by controlling physical attributes of projectiles. The mechanics of the game require the player to learn the basics of parabolic arcs, and friction in order to make use of the projectiles. Educational and learning theories are applied to the design in order to… (More)
Our research focuses on the problem of automatically acquiring structured narrative information from natural language. We have focused on character extraction and narrative role identification from a corpus of Slavic folktales. To address natural language processing (NLP) issues in this particular domain we have explored alternatives to linear pipelined… (More)
Existing work on player modeling often assumes that the play style of players is static. However, our recent work shows evidence that players regularly change their play style over time. In this paper we propose a novel player modeling framework to capture this change by using episodic information and sequential machine learning techniques. In particular,… (More)