1 - 4 of 4
ItemTraining IBM Watson Using Automatically Generated Question-Answer Pairs( 2017-01-04)IBM Watson is a cognitive computing system capable of question answering in natural languages. It is believed that IBM Watson can understand large corpora and answer relevant questions more effectively than any other question-answering system currently available. To unleash the full power of Watson, however, we need to train its instance with a large number of well-prepared question-answer pairs. Obviously, manually generating such pairs in a large quantity is prohibitively time consuming and significantly limits the efficiency of Watson’s training. Recently, a large-scale dataset of over 30 million question-answer pairs was reported. Under the assumption that using such an automatically generated dataset could relieve the burden of manual question-answer generation, we tried to use this dataset to train an instance of Watson and checked the training efficiency and accuracy. According to our experiments, using this auto-generated dataset was effective for training Watson, complementing manually crafted question-answer pairs. To the best of the authors’ knowledge, this work is the first attempt to use a large-scale dataset of automatically generated question-answer pairs for training IBM Watson. We anticipate that the insights and lessons obtained from our experiments will be useful for researchers who want to expedite Watson training leveraged by automatically generated question-answer pairs.
ItemThe Social Factory: Connecting People, Machines and Data in Manufacturing for Context-Aware Exception Escalation( 2017-01-04)Manufacturing environments are socio-technical systems \ where people have to interact with machines to achieve \ a common goal. The goal of the fourth industrial revolution is \ to improve their flexibility for mass customization and rapidly \ changing production conditions. As a contribution towards \ this goal, we introduce the Social Factory: a social network \ with a powerful analytics backend to improve the connection \ between the persons working in the production environment, \ the manufacturing machines, and the data that is created \ in the process. We represent machines, people and chatbots \ for information provisioning as abstract users in the social \ network. We enable natural language based communication between \ them and provide a rich knowledge base and automated \ problem solution suggestions. Access to complex production \ environments thus becomes intuitive, cooperation among users \ improves and problems are resolved more easily.
ItemRebuilding Evolution: A Service Science Perspective( 2017-01-04)This paper explores a simple idea and asks a simple question: What determines the speed limit of evolutionary processes, and might there be ways to speed up those processes for certain types of systems under certain conditions? Or even more simply, how rapidly can complex systems be rebuilt? To begin with, the universe can be viewed as an evolving ecology of entities. Entities correspond to types of systems - from atoms in stars to organisms on Earth to ideas in the heads of people. Service science is the study of the evolving ecology of service system entities, complex socio-technical systems with rights and responsibilities – such as people, businesses, and nations. We can only scratch the surface in this paper, but our explorations suggest this is an important research question and direction, especially as we enter the cognitive era of smart and wise service systems. For example, it takes a child multiple years of experience to learn language and basic social interactions skills, but could machine learning algorithms with the proper data sets learn those capabilities in a fraction of the time?