A more natural way for non-expert users to express their tasks in an open-ended set is to use natural language. In this case,a human-centered intelligent agent/robot is required to be able to understand and generate p...A more natural way for non-expert users to express their tasks in an open-ended set is to use natural language. In this case,a human-centered intelligent agent/robot is required to be able to understand and generate plans for these naturally expressed tasks. For this purpose, it is a good way to enhance intelligent robot's abilities by utilizing open knowledge extracted from the web, instead of hand-coded knowledge. A key challenge of utilizing open knowledge lies in the semantic interpretation of the open knowledge organized in multiple modes, which can be unstructured or semi-structured, before one can use it.Previous approaches used a limited lexicon to employ combinatory categorial grammar(CCG) as the underlying formalism for semantic parsing over sentences. Here, we propose a more effective learning method to interpret semi-structured user instructions. Moreover, we present a new heuristic method to recover missing semantic information from the context of an instruction. Experiments showed that the proposed approach renders significant performance improvement compared to the baseline methods and the recovering method is promising.展开更多
The paper proposes an open model for human computer interaction. It divides the interactive system into six layers: I/O media, concept, semantic/syntax, domain, mode/style, and computation, and adopts knowledge to rep...The paper proposes an open model for human computer interaction. It divides the interactive system into six layers: I/O media, concept, semantic/syntax, domain, mode/style, and computation, and adopts knowledge to represent functions of the layers. The paper outlines the open model and the knowledge used within each layer. The characteristics are also discussed. An example dialogue is given to clarify the idea.展开更多
随着教育大数据的兴起,学习者的画像变得更加精准、全面。如何从丰富的数据中提炼出有意义的信息,使其价值最大化是构建学习者模型的核心。传统的学习者模型虽然能为学习系统提供各类信息,但未赋予用户访问权限,用户无法参与模型的构建...随着教育大数据的兴起,学习者的画像变得更加精准、全面。如何从丰富的数据中提炼出有意义的信息,使其价值最大化是构建学习者模型的核心。传统的学习者模型虽然能为学习系统提供各类信息,但未赋予用户访问权限,用户无法参与模型的构建与控制。为更好地支持学习,实现学习过程的透明化,需要将学习者模型向用户开放。其开放的对象广泛,且意义不仅局限于基本的可视化。本期高阶访谈有幸邀请到国际知名教育人工智能专家朱迪·凯(Judy Kay)教授分享开放学习者模型的构建与应用的经验和见解。朱迪·凯教授是澳大利亚悉尼大学计算机科学教授,《教育人工智能国际期刊》(International Journal of Artificial Intelligence in Education)联合主编,研究领域为人机交互、普适计算和教育人工智能,研究重点是创建个性化终身全方位学习的基础设施、工具和界面,核心是开放学习者模型的界面设计,使用户能通过界面参与学习者模型构建。她在《教育人工智能国际期刊》《用户建模与用户自适应交互》(User Modeling and User-Adapted Interaction)、《个人与普适计算》(Personal and Ubiquitous Computing)、《计算机科学教育》(Computer Science Education)等国际知名期刊发表论文40余篇,并在界面研究方面创建了自然用户交互(Natural User Interaction)软件框架,为人们使用桌面、墙面等大型交互平面提供了新途径。展开更多
基金supported by the National Natural Science Foundation of China(61175057)the USTC Key-Direction Research Fund(WK0110000028)
文摘A more natural way for non-expert users to express their tasks in an open-ended set is to use natural language. In this case,a human-centered intelligent agent/robot is required to be able to understand and generate plans for these naturally expressed tasks. For this purpose, it is a good way to enhance intelligent robot's abilities by utilizing open knowledge extracted from the web, instead of hand-coded knowledge. A key challenge of utilizing open knowledge lies in the semantic interpretation of the open knowledge organized in multiple modes, which can be unstructured or semi-structured, before one can use it.Previous approaches used a limited lexicon to employ combinatory categorial grammar(CCG) as the underlying formalism for semantic parsing over sentences. Here, we propose a more effective learning method to interpret semi-structured user instructions. Moreover, we present a new heuristic method to recover missing semantic information from the context of an instruction. Experiments showed that the proposed approach renders significant performance improvement compared to the baseline methods and the recovering method is promising.
文摘The paper proposes an open model for human computer interaction. It divides the interactive system into six layers: I/O media, concept, semantic/syntax, domain, mode/style, and computation, and adopts knowledge to represent functions of the layers. The paper outlines the open model and the knowledge used within each layer. The characteristics are also discussed. An example dialogue is given to clarify the idea.
文摘随着教育大数据的兴起,学习者的画像变得更加精准、全面。如何从丰富的数据中提炼出有意义的信息,使其价值最大化是构建学习者模型的核心。传统的学习者模型虽然能为学习系统提供各类信息,但未赋予用户访问权限,用户无法参与模型的构建与控制。为更好地支持学习,实现学习过程的透明化,需要将学习者模型向用户开放。其开放的对象广泛,且意义不仅局限于基本的可视化。本期高阶访谈有幸邀请到国际知名教育人工智能专家朱迪·凯(Judy Kay)教授分享开放学习者模型的构建与应用的经验和见解。朱迪·凯教授是澳大利亚悉尼大学计算机科学教授,《教育人工智能国际期刊》(International Journal of Artificial Intelligence in Education)联合主编,研究领域为人机交互、普适计算和教育人工智能,研究重点是创建个性化终身全方位学习的基础设施、工具和界面,核心是开放学习者模型的界面设计,使用户能通过界面参与学习者模型构建。她在《教育人工智能国际期刊》《用户建模与用户自适应交互》(User Modeling and User-Adapted Interaction)、《个人与普适计算》(Personal and Ubiquitous Computing)、《计算机科学教育》(Computer Science Education)等国际知名期刊发表论文40余篇,并在界面研究方面创建了自然用户交互(Natural User Interaction)软件框架,为人们使用桌面、墙面等大型交互平面提供了新途径。
