Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement
نویسندگان
چکیده
منابع مشابه
Experience-Oriented Artificial Intelligence
AI is at an impasse. It is stuck, or downsizing. Unable to build large, ambitious systems because no means to manage complexity. Now people manage complexity, but a large AI must do it itself. An AI must be able to tell for itself when it is right and when it is wrong. Experience is the route to this... Experience should be at the center of AI. It is what AI is about. It is the data of AI, yet ...
متن کاملFrom Task-Oriented to Goal-Oriented Web Requirements Analysis
Task analysis has been used traditionally in HCI and CSCW to define requirements for user interfaces, webbased or otherwise. This paper argues that a shift of paradigm is needed in web engineering from taskoriented to goal-oriented approaches for designing applications delivering a quality user experience and achieving the objectives of the stakeholders. Task models focus on fine-grained and pr...
متن کاملIn Favor of Artificial Intelligence Methods for Bridging the Gap Between Command-Oriented System and Task-Oriented User Views
Progress in human-computer interaction constitutes, apart from the enormous success in hardware development, one of the most exiting and barely anticipated changes in the field of computer science over the past 20 years. However, despite considerable achievements obtained through e.g., graphical user interfaces and various sorts of adaptive tools, the comprehensibility of handling the increasin...
متن کاملFrom generic to task-oriented speech recognition :
This paper presents CLIPS laboratory activities in speech recognition related to language model adaptation and acoustic model adaptation in the NESPOLE! European project. ASR system needed to be adapted in two ways. The language model had to deal with task specific vocabulary and the acoustic model had to be robust to VoIP (Voice over IP) speech. It was shown that Internet, as a very large sour...
متن کاملMyworld: an Agent-oriented Testbed for Distributed Artificial Intelligence
Agent-Oriented Programming (AOP) is a new programming paradigm which proposes that mentalistic notions (such as belief, intention, commitment and so on) are useful abstraction mechanisms for describing complex, intelligent agents, and that they may therefore be used as a basis for programming such agents [17]. In this paper, we describe a Distributed Artificial Intelligence testbed called MYWOR...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Artificial Intelligence Review
سال: 2016
ISSN: 0269-2821,1573-7462
DOI: 10.1007/s10462-016-9505-7