Harvesting Wikipedia knowledge to identify topics in ongoing natural language dialogs
|Harvesting Wikipedia knowledge to identify topics in ongoing natural language dialogs|
|Author(s)||Breuing A., Waltinger U., Wachsmuth I.|
|Published in||Proceedings - 2011 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2011|
|Keyword(s)||Human- agent interaction, Information retrieval, Topic identification, Wikipedia (Extra: Agent interaction, Artificial agents, Category systems, Conversational agents, Encyclopedic knowledge, Graph-based representations, Identification process, Natural languages, Topic identification, Wikipedia, Information retrieval, User interfaces)|
|Article||BASE, CiteSeerX, Google Scholar|
|Web||Ask, Bing, Google (PDF), Yahoo!|
|Download and mirrors|
|Local copy||Not available|
|Remote mirror(s)||Not available|
|Export and share|
|BibTeX, CSV, RDF, JSON|
|Browse properties · List of conference papers|
Harvesting Wikipedia knowledge to identify topics in ongoing natural language dialogs is a 2011 conference paper written in English by Breuing A., Waltinger U., Wachsmuth I. and published in Proceedings - 2011 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2011.
This paper introduces a model harvesting the crowdsourced encyclopedic knowledge provided by Wikipedia to improve the conversational abilities of an artificial agent. More precisely, we present a model for automatic topic identification in ongoing natural language dialogs. On the basis of a graphbased representation of theWikipedia category system, our model implements six tasks essential for detecting the topical overlap of coherent dialog contributions. Thereby the identification process operates online to handle dialog streams of constantly changing topical threads in real-time. The realization of the model and its application to our conversational agent aims to improve humanagent conversations by transferring human-like topic awareness to the artificial interlocutor.
- This section requires expansion. Please, help!
Probably, this publication is cited by others, but there are no articles available for them in WikiPapers. Cited 4 time(s)