Processing open text input in a scripted communication scenario
SEMDIAL 2018 proceedings, November 2018
Authors
Raja Lala [1], Johan Jeuring [1,2], F.P.M. Heemskerk [1], Marcell van Geest [1], Jordy van Dortmont [1], Gabriel Gutu-Robu [3], Stefan Ruseti [3], Dascalu Mihai [3], Beatrice Alex [4,5], and Richard Tobin [4]
[1] Utrecht University Computer Science Department, Netherlands
[2] Faculty of Management, Science and Technology, Open University Netherlands
[3] University Politehnica of Bucharest, Computer Science Department, Romania
[4] University of Edinburgh, School of Informatics, United Kingdom
[5] The Alan Turing Institute, London, United Kingdom
Abstract
Serious games often employ pre-scripted dialogues and interactions with a player; in contrast to free user input that enables deeper immersion. In this paper we explore possibilities for interactive natural language dialogue in a serious game by combining Natural Language Processing (NLP) techniques with dialogue management. Our game learning environment has a communication scenario editor in which a domain expert develops a structured, scripted scenario as a sequence of potential interactions. A communication scenario is context-specific and often follows a protocol - for instance, delivering bad news to a patient. Currently, a player navigates through a simulation and converses with a virtual character by choosing a statement option from one of the prescripted player statements, at each step in the simulation. We develop a scenario-specific corpus method (SSCM) to process open responses (i.e. natural language inputs) in our learning environment. We conduct an experiment to collect data for comparing SSCM against multiple NLP methods, and another experiment to investigate if framing can improve processing open-text input using SSCM in a communication simulation.
View publication
Optimizing Draw Call Batching Using Transient Data-Guided Texture Atlases
Master’s thesis, November 24, 2017
Author
Jordy van Dortmont [1,2]
Supervisors
Bas Zalmstra [1], Wishnu Prasetya [2], Jacco Bikker [2]
[1] Abbey Games, [2] Utrecht University
Abstract
Rendering a large number of 2D textures in real-time requires reducing the overhead of a large number of draw calls on the CPU caused by binding different textures when drawing. Texture atlases are used to avoid switching textures by packing textures into one larger texture before rendering. Graphics hardware APIs limit the size of a texture, so textures need to be partitioned into multiple atlases. Unfortunately, composing textures into atlases is performed manually by developers or artists with an educated guess and requires manually checking which texture switch breaks a draw call batch to improve batching. Manual composition of texture atlases is cumbersome, time-consuming and not optimal for large-scale and unpredictable use of textures. We automated the composition of atlases based on previously gathered texture rendering data to remove manual intervention and created transient texture atlases at run-time based on usage to optimize draw call batching. We applied our approach to four simulations and measured the number of draw calls, CPU frame time and GPU frame time. The number of draw calls is similar or less for data-guided texture atlases than for manually composed texture atlases. Transient data-guided texture atlases reduce the number of draw calls significantly for unpredictable use of textures, which leads to performance gains on the CPU.
View publication
Scenarios in virtual learning environments for one-to-one communication skills training
International Journal of Educational Technology in Higher Education, May 11, 2017. Springer Open
Authors
Raja Lala, Johan Jeuring, Jordy van Dortmont, Marcell van Geest
Abstract
A scenario is a description of a series of interactions between a player and a virtual character for one-to-one communication skills training, where at each step the player is faced with a choice between statements. In this paper, we analyse the characteristics of scenarios and provide a classification to represent such scenarios. The analysis is performed through a literature review and by comparing virtual learning environments for scenario based training. Using this analysis we specify requirements for describing communication scenarios related to their: structure (linear, branching, interleaving), properties (static information stored per scenario like situation, background, which virtual character to show), and parameters (characteristics of a scenario that can be modified per statement like a score on a learning goal and an emotional effect in a virtual character). We define a schema for representing such communication scenarios and present an authoring tool to create a scenario.
View publication
An implementation architecture for scenario-based simulations
In: ITS 2016, 13th International Conference on Intelligent Tutoring Systems, Zagreb, Croatia, June 7-10, 2016. Springer, Lecture Notes in Computer Science 9684
Authors
Raja Lala, Johan Jeuring, Jordy van Dortmont
Abstract
The past years have witnessed an increased use of applied games for developing and evaluating communication skills. These skills benefit from interpersonal interactions. Providing feedback to students practicing communication skills is difficult in a traditional class setting with one teacher and many students. This logistic challenge may be partly overcome by providing training using a simulation in which a student practices with communication scenarios. A scenario is a description of a series of interactions, where at each step the player is faced with a choice. We have developed a scenario editor that enables teachers to develop scenarios for practicing communication skills. A teacher can develop a scenario without knowledge of the implementation. This paper presents the implementation architecture for such a scenario-based simulation.