Acquiring Trustworthy Knowledge for Conversation Agents based on a Web Knowledge Trust Model.

This paper presents a proposal to facilitate the use of online documents from the World Wide Web (WWW) - to acquire knowledge for intelligent Conversation Agents (CA). Information extracted from public web pages has--long been an issue that web pages may contain incorrect information or are outright hoaxes. Therefore, we propose a Web Knowledge Trust Model (WKTM) to find 'trustworthy' websites and to ensure the credibility and reliability of the knowledge extracted from the web-derived corpora. 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 conversation agent's domain knowledge base. [ABSTRACT FROM AUTHOR]