Difference between revisions of "Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models"
(Infobox work) |
(Embed) |
||
| Line 10: | Line 10: | ||
== Overview == | == Overview == | ||
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, authors 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. Authors investigate two different perspectives to the task of interfacing virtual agents with collaborative knowledge. First, authors exploit the use of [[Wikipedia categories]] as a basis for identifying the broader topic of a spoken utterance. Second, authors describe how to enhance the conversational behavior of the virtual agent by means of a Wikipedia-based question answering component which incorporates the question topic. At large, approach identifies topic-related focus terms of a user's question, which are subsequently mapped onto a category taxonomy. Thus, authors utilize the taxonomy as a reference point to derive topic labels for a user's question. The employed topic model is thereby based on explicitly given concepts as represented by the document and [[category structure]] of the Wikipedia knowledge base. Identified topic [[categories]] are subsequently combined with different linguistic filtering methods to improve answer candidate retrieval and reranking. Results show that the topic model approach contributes to an enhancement of the conversational behavior of virtual agents. | 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, authors 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. Authors investigate two different perspectives to the task of interfacing virtual agents with collaborative knowledge. First, authors exploit the use of [[Wikipedia categories]] as a basis for identifying the broader topic of a spoken utterance. Second, authors describe how to enhance the conversational behavior of the virtual agent by means of a Wikipedia-based question answering component which incorporates the question topic. At large, approach identifies topic-related focus terms of a user's question, which are subsequently mapped onto a category taxonomy. Thus, authors utilize the taxonomy as a reference point to derive topic labels for a user's question. The employed topic model is thereby based on explicitly given concepts as represented by the document and [[category structure]] of the Wikipedia knowledge base. Identified topic [[categories]] are subsequently combined with different linguistic filtering methods to improve answer candidate retrieval and reranking. Results show that the topic model approach contributes to an enhancement of the conversational behavior of virtual agents. | ||
| + | |||
| + | == Embed == | ||
| + | === Wikipedia Quality === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | Waltinger, Ulli; Breuing, Alexa; Wachsmuth, Ipke. (2011). "[[Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models]]". AAAI Press. DOI: 10.5591/978-1-57735-516-8/IJCAI11-317. | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | === English Wikipedia === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | {{cite journal |last1=Waltinger |first1=Ulli |last2=Breuing |first2=Alexa |last3=Wachsmuth |first3=Ipke |title=Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models |date=2011 |doi=10.5591/978-1-57735-516-8/IJCAI11-317 |url=https://wikipediaquality.com/wiki/Interfacing_Virtual_Agents_with_Collaborative_Knowledge:_Open_Domain_Question_Answering_Using_Wikipedia-Based_Topic_Models |journal=AAAI Press}} | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | === HTML === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | Waltinger, Ulli; Breuing, Alexa; Wachsmuth, Ipke. (2011). &quot;<a href="https://wikipediaquality.com/wiki/Interfacing_Virtual_Agents_with_Collaborative_Knowledge:_Open_Domain_Question_Answering_Using_Wikipedia-Based_Topic_Models">Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models</a>&quot;. AAAI Press. DOI: 10.5591/978-1-57735-516-8/IJCAI11-317. | ||
| + | </nowiki> | ||
| + | </code> | ||
Revision as of 09:47, 1 August 2019
Authors | Ulli Waltinger Alexa Breuing Ipke Wachsmuth |
|---|---|
Publication date | 2011 |
DOI | 10.5591/978-1-57735-516-8/IJCAI11-317 |
Links | Original |
Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models - scientific work related to Wikipedia quality published in 2011, written by Ulli Waltinger, Alexa Breuing and Ipke Wachsmuth.
Overview
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, authors 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. Authors investigate two different perspectives to the task of interfacing virtual agents with collaborative knowledge. First, authors exploit the use of Wikipedia categories as a basis for identifying the broader topic of a spoken utterance. Second, authors describe how to enhance the conversational behavior of the virtual agent by means of a Wikipedia-based question answering component which incorporates the question topic. At large, approach identifies topic-related focus terms of a user's question, which are subsequently mapped onto a category taxonomy. Thus, authors utilize the taxonomy as a reference point to derive topic labels for a user's question. The employed topic model is thereby based on explicitly given concepts as represented by the document and category structure of the Wikipedia knowledge base. Identified topic categories are subsequently combined with different linguistic filtering methods to improve answer candidate retrieval and reranking. Results show that the topic model approach contributes to an enhancement of the conversational behavior of virtual agents.
Embed
Wikipedia Quality
Waltinger, Ulli; Breuing, Alexa; Wachsmuth, Ipke. (2011). "[[Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models]]". AAAI Press. DOI: 10.5591/978-1-57735-516-8/IJCAI11-317.
English Wikipedia
{{cite journal |last1=Waltinger |first1=Ulli |last2=Breuing |first2=Alexa |last3=Wachsmuth |first3=Ipke |title=Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models |date=2011 |doi=10.5591/978-1-57735-516-8/IJCAI11-317 |url=https://wikipediaquality.com/wiki/Interfacing_Virtual_Agents_with_Collaborative_Knowledge:_Open_Domain_Question_Answering_Using_Wikipedia-Based_Topic_Models |journal=AAAI Press}}
HTML
Waltinger, Ulli; Breuing, Alexa; Wachsmuth, Ipke. (2011). "<a href="https://wikipediaquality.com/wiki/Interfacing_Virtual_Agents_with_Collaborative_Knowledge:_Open_Domain_Question_Answering_Using_Wikipedia-Based_Topic_Models">Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models</a>". AAAI Press. DOI: 10.5591/978-1-57735-516-8/IJCAI11-317.
