Trust Based Knowledge Acquisition for Conversation Agents

نویسندگان

  • Ong Sing Goh
  • Chun Che Fung
چکیده

This paper explores the study of conversation agent knowledge bases particularly, its relationship to the related study of information trustworthiness and knowledge acquisition. Some important methods for knowledge extraction from online documents are discussed in this paper. This is done in relation to the purpose of the design and development of domain-specific information for CAs’ knowledge bases. This paper focuses on a novel approach based on the proposed Web Knowledge Trust Model (WKTM) and the Automated Knowledge Extraction Agent (AKEA). The results indicate that WKTM is useful for evaluating the trustworthiness of web sites and it is useful for the developing of key criteria for a knowledge acquisition for conversation agents.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Model of Culture in Trading Agents

Geert Hofstede’s five-dimensional framework is widely used in social sciences and management science to characterize cultures. It has been suggested to build culturally consistent agent characters based on his framework. This chapter stresses the relevance of culture and trust for trade, substantiates why a dimensional model offers a good basis for cultural differentiation of agents, and presen...

متن کامل

Comparing Experiential Approaches: Structured Language Learning Experiences versus Conversation Partners for Changing Pre-Service Teacher Beliefs

Research has shown that language teachers’ beliefs are often difficult to change through education.  Experiential learning may help, but more research is needed to understand how experiential approaches shape perceptions. This study compares two approaches, conversation partners (CONV) and structured language learning experiences (SLLE), integrated into a course in language acquisition. Partici...

متن کامل

The Design of a Coordination Language for Multi-Agent Systems

The agent view provides a level of abstraction at which we envisage computational systemscarrying out cooperative work by interoperating across networked people, organizations and machines. A major challenge in building such systems is coordinating the behavior of the individual agents to achieve the individual and shared goals of the participants. In this paper we propose a conceptualization o...

متن کامل

On How Agents Make Friends: Mechanisms for Trust Acquisition

We need models of trust to facilitate cooperation in multi-agent systems, where agents, human and artificial, do not know each other beforehand. This paper lists and proposes simple mechanisms for trust acquisition based on a very basic and general definition of trust, making no assumptions on the internal cognitive models of the involved agents. We also show how trust acquired one-on-one can b...

متن کامل

The Dangers Of Invisible Computing: Learning To Live with Uncertainty

The comfortable certainties about the nature of trust on which most conventional security systems have been founded have always been at best doubtful. In pervasive computing environments they become both delusional and dangerous. As a consequence, it is necessary for both technically aware service providers and technically naïve end users to abandon the false hope that the behaviour of secure p...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008