STORYEVAL: An Empirical Evaluation Framework for Narrative Generation

نویسندگان

  • Jonathan P. Rowe
  • Scott W. McQuiggan
  • Jennifer L. Robison
  • Derrick R. Marcey
  • James C. Lester
چکیده

Research in intelligent narrative technologies has recently experienced a significant resurgence. As the field matures, devising principled evaluation methodologies will become increasingly important to ensure continued progress. Because of the complexities of narrative phenomena, as well as the inherent subjectivity of narrative experiences, effectively evaluating intelligent narrative technologies poses significant challenges. In this paper, we present STORYEVAL, an evaluation framework for empirically studying computational models of narrative generation. Drawing on evaluation methodologies from cognitive science, human-computer interaction, and natural language processing, as well as techniques that have begun to emerge in the narrative technologies community, STORYEVAL consists of four complementary tools for evaluating both interactive and non-interactive narrative generation: Narrative Metrics, Cognitive-Affective Studies, Directorcentric Studies, and Extrinsic Narrative Evaluations. We discuss the benefits and limitations of each family of techniques and illustrate their application with example narrative generators drawn from the field.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Evaluating Analogy-Based Story Generation: An Empirical Study

Evaluation is one of the major open problems in computational narrative. In this paper, we present an empirical study of SAM, an analogy-based story generation (ASG) algorithm, that was created as part of our Riu interactive narrative system. Specifically, our study focuses on SAM’s capability to retrieve and generate short non-interactive stories. Combining qualitative and quantitative methods...

متن کامل

Cognitive models of discourse comprehension for narrative generation

This article presents an approach to using cognitive models of narrative discourse comprehension to define an explicit computational model of a reader’s comprehension process during reading, predicting aspects of narrative focus and inferencing with precision. This computational model is employed in a narrative discourse generation system to select and sequence content from a partial plan repre...

متن کامل

Modeling User Knowledge with Dynamic Bayesian Networks in Interactive Narrative Environments

Recent years have seen a growing interest in interactive narrative systems that dynamically adapt story experiences in response to users’ actions, preferences, and goals. However, relatively little empirical work has investigated runtime models of user knowledge for informing interactive narrative adaptations. User knowledge about plot scenarios, story environments, and interaction strategies i...

متن کامل

CRYSTAL ISLAND: A Narrative-Centered Learning Environment for Eighth Grade Microbiology

Narrative-centered learning environments offer significant promise for promoting interactive learning experiences that are both effective and engaging. Models of narrative generation and reasoning can balance the motivational and pedagogical aspects of narrative-centered learning interactions. Affect recognition and affect expression models are useful for shaping students’ affective trajectorie...

متن کامل

Data envelopment analysis in service quality evaluation: an empirical study

Service quality is often conceptualized as the comparison between service expectations and the actual performance perceptions. It enhances customer satisfaction, decreases customer defection, and promotes customer loyalty. Substantial literature has examined the concept of service quality, its dimensions, and measurement methods. We introduce the perceived service quality index (PSQI) as a sing...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009