An important challenge in interactive machine learning, particularly in subjective or ambiguous domains, is fostering bi-directional alignment between humans and models. Users teach models their concept definition through data labeling, while refining their own understandings throughout the process. To facilitate this, we introduce MOCHA, an interactive machine learning tool informed by two theories of human concept learning and cognition. First, it utilizes a neuro-symbolic pipeline to support Variation Theory-based counterfactual data generation. By asking users to annotate counterexamples that are syntactically and semantically similar to already-annotated data but predicted to have different labels, the system can learn more effectively while helping users understand the model and reflect on their own label definitions. Second, MOCHA uses Structural Alignment Theory to present groups of counterexamples, helping users comprehend alignable differences between data items and annotate them in batch. We validated MOCHA's effectiveness and usability through a lab study with 18 participants.
Teaching Spell Checkers to Teach: Pedagogical Program Synthesis for Interactive Learning
Georgia Institute of Technology(佐治亚理工学院);Stanford University(斯坦福大学);University of Buffalo(布法罗大学);University of Nevada , Reno(内华达大学里诺分校);University at Buffalo(布法罗大学)
Bringing Cognitive Augmentation to Web Browsing Accessibility
Politecnico di Milano(米兰理工大学);University of Claude Bernard Lyon 1(里昂第一大学(克洛德·贝尔纳大学))
在本文中,我们将探讨认知增强带来的机会,以提供更自然和更方便的Web浏览体验。我们探索这些机会,通过\textit{conversational web browsing},一个新兴的互动模式,使盲人和视障用户(BVIP),以及普通用户,通过会话代理访问网站的内容和功能。通知的文献,我们以前的工作和原型设计练习,我们得到一个概念框架,支持BVIP会话的Web浏览需求,然后专注于自动提供这种支持的挑战,描述我们的早期工作和原型,利用只考虑结构和内容功能的算法。