This survey highlights the complexity of language and the challenge of developing AI algorithms capable of understanding and generating language. Over the past two decades, language modelling has evolved from statistical models to neural models, with recent advances in pre-trained language models (PLMs) that use Transformer models and large-scale corpora for improved language understanding and… Continue reading A Survey of Large Language Models
Archives: Resources
Resource description
Learning to Quantify
This book provides an introduction and an overview of learning to quantify (a.k.a. “quantification”), the task of training, by means of supervised learning, estimators of class proportions in unlabelled data. In data science, learning to quantify is a task of its own, related to classification but different from it, since estimating class proportions by simply… Continue reading Learning to Quantify
Search-Based Procedural Content Generation: A Taxonomy and Survey
The focus of this survey is on research in applying evolutionary and other metaheuristic search algorithms to automatically generating content for games, both digital and nondigital (such as board games). The term search-based procedural content generation is proposed as the name for this emerging field, which at present is growing quickly. A taxonomy for procedural… Continue reading Search-Based Procedural Content Generation: A Taxonomy and Survey
The Ordinal Nature of Affect: An Emerging Approach
Computational representation of everyday emotional states is a challenging task and, arguably, one of the most fundamental for affective computing. Standard practice in emotion annotation is to ask people to assign a value of intensity or a class value to each emotional behavior they observe. Psychological theories and evidence from multiple disciplines including neuroscience, economics and artificial intelligence, however, suggest that the task of assigning reference-based values to subjective notions is better aligned with the underlying representations. This paper draws together the theoretical reasons to favor ordinal labels for representing and annotating emotion, reviewing the literature across several disciplines. We go on to discuss good and bad practices of treating ordinal and other forms of annotation data and make the case for preference learning methods as the appropriate approach for treating ordinal labels. We finally discuss the advantages of ordinal annotation with respect to both reliability and validity through a number of case studies in affective computing, and address common objections to the use of ordinal data. More broadly, the thesis that emotions are by nature ordinal is supported by both theoretical arguments and evidence, and opens new horizons for the way emotions are viewed, represented and analyzed computationally.
Experience Driven Content Generation
Procedural content generation (PCG) is an increasingly important area of technology within modern human-computer interaction (HCI) design. Personalization of user experience via affective and cognitive modeling, coupled with real-time adjustment of the content according to user needs and preferences are important steps toward effective and meaningful PCG. Games, Web 2.0, interface, and software design are among the most popular applications of automated content generation. The paper provides a taxonomy of PCG algorithms and introduces a framework for PCG driven by computational models of user experience. This approach, which we call Experience-Driven Procedural Content Generation (EDPCG), is generic and applicable to various subareas of HCI. We employ games as an example indicative of rich HCI and complex affect elicitation, and demonstrate the approach’s effectiveness via dissimilar successful studies.
Artificial Intelligence and Games Textbook
This book aims to be the first comprehensive textbook on the application and use of artificial intelligence (AI) in, and for, games. Our hope is that the book will be used by educators and students of graduate or advanced undergraduate courses on game AI as well as game AI practitioners at large.