Dialogue Generation in Character-based Interactive Storytelling

Dialogue Generation in Character-based Interactive Storytelling
复制标题

基于角色的互动叙事中的对话生成

DOI:
--
复制
发表时间:
2005
期刊:
Artificial Intelligence and Interactive Digital Entertainment Conference
影响因子:
--
通讯作者:
Fred Charles
Fred Charles
中科院分区:
--
文献类型:
--
作者:
M. Cavazza;Fred Charles

文献摘要

被引文献

相似文献

近年来,在开发交互式讲故事系统方面取得了重大进展,特别是在底层人工智能技术方面。关于人工智能方法,特别是规划系统的使用,已经形成了共识。然而,这些都集中在一系列叙事行动的产生,通过虚拟演员的行为上演。为了实现实现再现传统电影美学品质的交互式媒体的长期目标,大多数交互式讲故事系统仍然缺少在角色之间生成对话的能力。我们描述了一个扩展我们的互动讲故事的方法,它集成了叙事情况下的对话生成。我们的生成单位是对话行为(一对话语),一个主要目标是再现现实的对话现象的基础上隐含的表达形式。重点还在于采用一种统一的方法,将叙事表征与生成的话语的语言形式联系起来。从积极的叙事目标和人物之间的情感亲和力的表示,我们的系统是能够得到一组参数管理的语言形式的各个方面要生成的。我们说明这种方法在几个实施的例子。
In recent years, there has been significant progress in developing Interactive Storytelling systems, in particular in terms of the underlying AI techniques. There has been an emerging consensus on the AI approach, in particular the use of planning systems. However, these have concentrated on the generation of a sequence of narrative actions, staged through the behaviour of virtual actors. In order to achieve the long-term objective of implementing interactive media that would reproduce the aesthetic qualities of traditional films, most interactive storytelling systems are still missing the ability to generate dialogues between characters. We describe an extension of our Interactive Storytelling approach which integrates dialogue generation within narrative situations. Our unit of generation is the dialogue act (pair of utterances) and one main objective is to reproduce realistic dialogue phenomena based on implicit forms of expression. The emphasis is also on adopting a unified approach relating narrative representations to the linguistic form of the generated utterances. From a representation of active narrative goals and the emotional affinity between characters, our system is able to derive a set of parameters governing various aspects of the linguistic form to be generated. We illustrate this approach on several implemented examples.