Expressive NLG for Next-Generation Learning Environments: Language, Affect, and Narrative
نویسنده
چکیده
Recent years have seen the appearance of adaptive learning technologies that offer significant potential for bringing about fundamental improvements in education. A promising development in this arena is the emergence of narrative-centered learning environments, which integrate the inferential capabilities of intelligent tutoring systems with the rich gameplay supported by commercial game engines. While narrative-centered learning environments have demonstrated effectiveness in both student learning and engagement, their capabilities will increase dramatically with expressive NLG. In this talk we will introduce the principles motivating the design of narrative-centered learning environments, discuss the role of NLG in narrative-centered learning, consider the interaction of NLG, affect, and learning, and explore how next-generation learning environments will push the envelope in expressive NLG. Biography Dr. James Lester is a professor Department of Computer Science North Carolina State University. He received the B.A. (Highest Honors), M.S.C.S., and Ph.D. Degrees in Computer Science from the University of Texas at Austin and the B.A in History from Baylor University. A member of Phi Beta Kappa, he has served as Program Chair for the ACM conference on Intelligent User Interfaces (2001), Program Chair for the International Conference on Intelligent Tutoring Systems (2004), Conference CoChair for the International Conference on Intelligent Virtual Agents (2008), and on the editorial board of Autonomous Agents and Multi-Agent Systems (1997-2007). His research focuses on intelligent tutoring systems, computational linguistics, and intelligent user interfaces. It has been recognized by several Best Paper awards. His research interests include intelligent game-based learning environments, computational models of narrative, affective computing, creativity-enhancing technologies, and tutorial dialogue. He is Editor-In-Chief of the International Journal of Artificial Intelligence in Education.
منابع مشابه
Evaluation in Natural Language Generation: The Question Generation Task
Question Generation (QG) is proposed as a shared-task evaluation campaign for evaluating Natural Language Generation (NLG) research. QG is a subclass of NLG that plays an important role in learning environments, information seeking, and other applications. We describe a possible evaluation framework for standardized evaluation of QG that can be used for black-box evaluation, for finer-grained e...
متن کاملAutomatic generation of conversational utterances and narrative for Augmentative and Alternative Communication: a prototype system
We detail the design, development and evaluation of Augmentative and Alternative Communication (AAC) software which encourages rapid conversational interaction. The system uses Natural Language Generation (NLG) technology to automatically generate conversational utterances from a domain knowledge base modelled from content suggested by a small AAC user group. Findings from this work are present...
متن کاملLearning what to say and how to say it: Joint optimisation of spoken dialogue management and natural language generation
This paper argues that the problems of dialogue management (DM) and Natural Language Generation (NLG) in dialogue systems are closely related and can be fruitfully treated statistically, in a joint optimisation framework such as that provided by Reinforcement Learning (RL). We first review recent results and methods in automatic learning of dialogue management strategies for spoken and multimod...
متن کاملGenerating Instructions in Virtual Environments (GIVE): A Challenge and an Evaluation Testbed for NLG
Would it be helpful or detrimental for the field of NLG to have a generally accepted competition? Competitions have definitely advanced the state of the art in some fields of NLP, but the benefits sometimes come at the price of over-competitiveness, and there is a danger of overfitting systems to the concrete evaluation metrics. Moreover, it has been argued that there are intrinsic difficulties...
متن کاملA working, non-trivial, topically indifferent NLG System for 17 languages
We present a fully fledged practical working application for a rule-based NLG system that is able to create non-trivial, human sounding narrative from structured data, in any language (e.g., English, German, Arabic and Finnish) and for any topic.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012