Equipping a Conversational Agent with Access to Wikipedia Knowledge

نویسنده

  • Alexa Breuing
چکیده

The online encyclopedia Wikipedia has become a popular source of knowledge and often constitutes the first choice for humans looking up information on the internet. Thereby, additional characteristics like the categorization of articles and the allocation of disambiguation pages support Wikipedia users in their search for the relevant article. By representing this information in an adequate format, machines are already able to process and use these additional hints as well. In the KnowCIT project we focus on extending the conversational abilities of the embodied conversational agent Max (Kopp et al. 2005) by accessing Wikipedia as an external source of information. This allows Max to look up information on Wikipedia similar to humans and to employ encyclopedic knowledge on request. More precisely, if the human dialog partner asks for information about a term which is not contained in the agent's present knowledge base so far, the system searches for an adequate Wikipeda article. A successful article search leads

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

Conversational Knowledge Teaching Agent that uses a Knowledge Base

When implementing a conversational educational teaching agent, user-intent understanding and dialog management in a dialog system are not sufficient to give users educational information. In this paper, we propose a conversational educational teaching agent that gives users some educational information or triggers interests on educational contents. The proposed system not only converses with a ...

متن کامل

Static and Dynamic Knowledge for the Embodied Conversational Agent Max - a First Approach -

The online encyclopedia Wikipedia is currently one of the best known collaboratively edited knowledge sources. While humans are able to inform themselves by reading the according articles in Wikipedia, machines lack the ability to understand natural language. Thus, a central task of bridging this deficit is the text technological reconstruction of the information held in Wikipedia to make this ...

متن کامل

Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models

This paper is concerned with the use of conversational agents as an interaction paradigm for accessing open domain encyclopedic knowledge by means of Wikipedia. More precisely, we describe a dialog-based question answering system for German which utilizes Wikipedia-based topic models as a reference point for context detection and answer prediction. We investigate two different perspectives to t...

متن کامل

Participation and Scientific Collaboration in Persian Wikipedia

Background and Aim: This research studies the effective participation and scientific collaboration in Persian Wikipedia, from 2003-2012.  Method: The library method has been used. Also, considering the objectives and the nature of subject, the research method is a descriptive-applied and during its implementation scientometric technique has been used. Excel and SPSS softwares have been used for...

متن کامل

Talking Topically to Artificial Dialog Partners: Emulating Humanlike Topic Awareness in a Virtual Agent

During dialog, humans are able to track ongoing topics, to detect topical shifts, to refer to topics via labels, and to decide on the appropriateness of potential dialog topics. As a result, they interactionally produce coherent sequences of spoken utterances assigning a thematic structure to the whole conversation. Accordingly, an artificial agent that is intended to engage in natural and soph...

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 2010