RSS Feed
KnowCIT |
Knowledge Enhanced Embodied Cognitive Interaction Technology
- Supervisor(s): Ipke Wachsmuth, Alexander Mehler (until 2010-09)
- Project Member(s): Alexa Breuing, Ulli Waltinger (from 2010-10),
Research Area: C
|
|
|
Abstract
In the KnowCIT project we extend the conversational abilities of the conversational agent MAX by equipping him with access to collaboratively constructed knowledge drawn from the online encyclopedia Wikipedia. By means of the crowd-sourced knowledge resource, the agent is able to identify, label, track, and continue the topic of a dialog as the interlocutor of a human dialog partner. This allows him to answer questions, to detect topic changes and to react meaningfully to the challenge of dialogical dynamics.
Research Questions and Methods
In the project we aim to connect two yet unrelated areas of modeling cognitive systems with semantic-web technologies. This relates to distributed cognition as exemplified by rising web technologies – e.g. social ontologies – on the one hand and artificial cognition based on embodied virtual agents – e.g. MAX – on the other hand.
read more »
Outcomes
A milestone of the KnowCIT project is the implementation of an open topic model that enables the artificial agent to identify and label the topic of a dialog to which he participates as an interlocutor of a human user. By interfacing the conceptual structures of Wikipedia, the project endows MAX with the capability to utilize more than 55,000 different thematic categories for the task of topic labeling. Another milestone of the KnowCIT project is its question-answering component. That is, KnowCIT enables MAX to exploit the document collection of Wikipedia by utilizing propositional information about more than 1.1 million entities for the task of knowledge representation and reasoning. Thereby, the topic model provides the basis to determine the set of topic-related patterns needed for hypothesis generation and answer candidate scoring. The resultant question-answering component invites human dialog partners to ask natural language questions and to explore the encyclopedic knowledge of Wikipedia just by means of interacting with a charming conversational agent.
Publications
Let's Talk Topically with Artificial Agents! Providing Agents with Humanlike Topic Awareness in Everyday Dialog Situations
Breuing A, Wachsmuth I (2012)
In: Proceedings of the 4th International Conference on Agents and Artificial Intelligence (ICAART). 22012. Portugal: SciTePress: 62 - 71.
In: Proceedings of the 4th International Conference on Agents and Artificial Intelligence (ICAART). 22012. Portugal: SciTePress: 62 - 71.
Conference Proceeding/Paper
|
Published
|
English
Harvesting Wikipedia Knowledge to Identify Topics in Ongoing Natural Language Dialogs
Breuing A, Waltinger U, Wachsmuth I (2011)
In: Proceedings of the 2011 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2011). Lyon, France: IEEE: 445 - 450.
In: Proceedings of the 2011 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2011). Lyon, France: IEEE: 445 - 450.
Conference Proceeding/Paper
|
Published
|
English
Authors:
Breuing, Alexa
;
Waltinger, Ulli
;
Wachsmuth, Ipke
Department:
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
AG Wissensbasierte Systeme
Center of Excellence - Cognitive Interaction Technology CITEC
AG Wissensbasierte Systeme
Abstract:
This paper introduces a model harvesting the crowd-sourced 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 graph-based representation of the Wikipedia 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 human-agent conversations by transferring human-like topic awareness to the artificial interlocutor.
This paper introduces a model harvesting the crowd-sourced 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 graph-based representation of the Wikipedia 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 human-agent conversations by transferring human-like topic awareness to the artificial interlocutor.
ISBN:
978-1-4577-1373-6
PUB-ID:
2144354 | Link: http://pub.uni-bielefeld.de/publication/2144354
Interfacing Virtual Agents With Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-based Topic Models
Waltinger U, Breuing A, Wachsmuth I (2011)
In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI–11). Walsh T (Ed.); Barcelona, Spain: AAAI Press: 1896 - 1902.
In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI–11). Walsh T (Ed.); Barcelona, Spain: AAAI Press: 1896 - 1902.
Conference Proceeding/Paper
|
Published
|
English
Authors:
Waltinger, Ulli
;
Breuing, Alexa
;
Wachsmuth, Ipke
Editors:
Walsh, T.
Department:
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
AG Wissensbasierte Systeme
Center of Excellence - Cognitive Interaction Technology CITEC
AG Wissensbasierte Systeme
ISBN:
978-1-57735-516-8
PUB-ID:
2144342 | Link: http://pub.uni-bielefeld.de/publication/2144342
Equipping a Conversational Agent with Access to Wikipedia Knowledge
Breuing A, Wachsmuth I (2010)
In: Proceedings of the KogWis 2010. Potsdam: Universitätsverlag Potsdam: 89 - 89.
In: Proceedings of the KogWis 2010. Potsdam: Universitätsverlag Potsdam: 89 - 89.
Conference Proceeding/Paper
|
Published
|
English
Interfacing a Conversational Agent with Contextual Knowledge Drawn from Wikipedia
Breuing A (2010)
In: Proceedings of the KogWis 2010. Potsdam: Universitätsverlag Potsdam: 58 - 59.
In: Proceedings of the KogWis 2010. Potsdam: Universitätsverlag Potsdam: 58 - 59.
Conference Proceeding/Paper
|
Published
|
English
Improving Human-Agent Conversations by Accessing Contextual Knowledge from Wikipedia
Breuing A (2010)
In: Proceedings of the 3rd WI-IAT Doctoral Workshop, in conj. with the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. Toronto, Canada: IEEE: 428 - 431.
In: Proceedings of the 3rd WI-IAT Doctoral Workshop, in conj. with the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. Toronto, Canada: IEEE: 428 - 431.
Conference Proceeding/Paper
|
Published
|
English
GermanPolarityClues: A Lexical Resource for German Sentiment Analysis
Waltinger U (2010)
In: Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10). Nicoletta Calzolari (Conference Chair) BMKC (Ed.); Valletta, Malta: European Language Resources Association (ELRA).
In: Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10). Nicoletta Calzolari (Conference Chair) BMKC (Ed.); Valletta, Malta: European Language Resources Association (ELRA).
Conference Proceeding/Paper
|
Published
|
English
Authors:
Waltinger, Ulli
Editors:
Nicoletta Calzolari (Conference Chair), Bente Maegaard Khalid Choukri
Department:
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
AG Wissensbasierte Systeme
Center of Excellence - Cognitive Interaction Technology CITEC
AG Wissensbasierte Systeme
ISBN:
2-9517408-6-7
PUB-ID:
1904061 | Link: http://pub.uni-bielefeld.de/publication/1904061
Sentiment Analysis Reloaded: A Comparative Study On Sentiment Polarity Identification Combining Machine Learning And Subjectivity Features
Waltinger U (2010)
In: Proceedings of the 6th International Conference on Web Information Systems and Technologies (WEBIST '10). Valencia, Spain.
In: Proceedings of the 6th International Conference on Web Information Systems and Technologies (WEBIST '10). Valencia, Spain.
Conference Proceeding/Paper
|
Published
|
English
Enhancing document modeling by means of open topic models Crossing the frontier of classification schemes in digital libraries by example of the DDC
Mehler A, Waltinger U (2009)
Library Hi Tech 27(4): 520 - 539.
Library Hi Tech 27(4): 520 - 539.
Journal Article
|
Published
|
English
Authors:
Mehler, Alexander
;
Waltinger, Ulli
Department:
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
Center of Excellence - Cognitive Interaction Technology CITEC
Abstract:
Purpose - The purpose of this paper is to present a topic classification model using the Dewey Decimal Classification (DDC) as the target scheme. This is to be done by exploring metadata. as provided by the Open Archives Initiative (OAT) to derive document snippets as minimal document representations. The reason is to reduce the effort of document processing in digital libraries. Further, the paper seeks to perform feature selection and extension by means of social ontologies and related web-based lexical resources. This is done to provide reliable topic-related classifications while circumventing the problem of data sparseness. Finally, the paper aims to evaluate the model by means of two language-specific corpora. The paper bridges digital libraries, on the one hand, and computational linguistics, on the other. The aim is to make accessible computational linguistic methods to provide thematic classifications in digital libraries based on closed topic models such as the DDC. Design/methodology/approach - The approach takes the form of text classification, text-technology, computational linguistics, computational semantics, and social semantics. Findings - It is shown that SVM-based classifiers perform best by exploring certain selections of OAI document metadata. Research limitations/implications - The findings show that it is necessary to further develop SVM-based DDC-classifiers by using larger training sets possibly for more than two languages in order to get better F-measure values. Originality/value - Algorithmic and formal-mathematical information is provided on how to build DDC-classifiers for digital libraries.
Purpose - The purpose of this paper is to present a topic classification model using the Dewey Decimal Classification (DDC) as the target scheme. This is to be done by exploring metadata. as provided by the Open Archives Initiative (OAT) to derive document snippets as minimal document representations. The reason is to reduce the effort of document processing in digital libraries. Further, the paper seeks to perform feature selection and extension by means of social ontologies and related web-based lexical resources. This is done to provide reliable topic-related classifications while circumventing the problem of data sparseness. Finally, the paper aims to evaluate the model by means of two language-specific corpora. The paper bridges digital libraries, on the one hand, and computational linguistics, on the other. The aim is to make accessible computational linguistic methods to provide thematic classifications in digital libraries based on closed topic models such as the DDC. Design/methodology/approach - The approach takes the form of text classification, text-technology, computational linguistics, computational semantics, and social semantics. Findings - It is shown that SVM-based classifiers perform best by exploring certain selections of OAI document metadata. Research limitations/implications - The findings show that it is necessary to further develop SVM-based DDC-classifiers by using larger training sets possibly for more than two languages in order to get better F-measure values. Originality/value - Algorithmic and formal-mathematical information is provided on how to build DDC-classifiers for digital libraries.
Keywords:
Digital libraries ;
Modelling ;
Document management
ISSN:
0737-8831
PUB-ID:
1588836 | Link: http://pub.uni-bielefeld.de/publication/1588836
Social Semantics and Its Evaluation by Means of Semantic Relatedness and Open Topic Models
Waltinger U, Mehler A (2009)
In: Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology. 1. Washington, DC, USA: IEEE Computer Society: 42 - 49.
In: Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology. 1. Washington, DC, USA: IEEE Computer Society: 42 - 49.
Conference Proceeding/Paper
|
Published
|
English
Authors:
Waltinger, Ulli
;
Mehler, Alexander
Department:
X1 - Multimodal alignment corpora: ...
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
ISBN:
978-0-7695-3801-3
PUB-ID:
1904125 | Link: http://pub.uni-bielefeld.de/publication/1904125
Social Semantics And Its Evaluation By Means of Closed Topic Models: An SVM-Classification Approach Using Semantic Feature Replacement By Topic Generalization
Waltinger U, Mehler A, Gleim R (2009)
In: Proceedings of the GSCL-Conference 2009. Potsdam, Germany.
In: Proceedings of the GSCL-Conference 2009. Potsdam, Germany.
Download:
Conference Proceeding/Paper
|
Published
|
English
Authors:
Waltinger, Ulli
;
Mehler, Alexander
;
Gleim, Rüdiger
Department:
X1 - Multimodal alignment corpora: ...
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
PUB-ID:
1904121 | Link: http://pub.uni-bielefeld.de/publication/1904121
From Social Networks To Distributional Properties: A Comparative Study On Computing Semantic Relatedness
Waltinger U, Cramer I, Wandmacher T (2009)
In: Proceedings of the 31th Annual Conference of the Cognitive Science Society. Taatgen NA, Rijn van H (Eds.); Austin, TX: Cognitive Science Society: 3016 - 3021.
In: Proceedings of the 31th Annual Conference of the Cognitive Science Society. Taatgen NA, Rijn van H (Eds.); Austin, TX: Cognitive Science Society: 3016 - 3021.
Conference Proceeding/Paper
|
Published
|
English
Authors:
Waltinger, Ulli
;
Cramer, Irene
;
Wandmacher, Tonio
Editors:
Taatgen, N.A.
;
Rijn van, H.
Department:
X1 - Multimodal alignment corpora: ...
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
Technische Fakultät
Center of Excellence - Cognitive Interaction Technology CITEC
PUB-ID:
1904115 | Link: http://pub.uni-bielefeld.de/publication/1904115
WikiDB: Building Interoperable Wiki-Based Knowledge Resources for Semantic Databases
Mehler A, Gleim R, Ernst A, Waltinger U (2008)
Sprache und Datenverarbeitung. International Journal for Language Data Processing 32(1).
Sprache und Datenverarbeitung. International Journal for Language Data Processing 32(1).
Download:
Journal Article
|
Published
|
English
Authors:
Mehler, Alexander
;
Gleim, Rüdiger
;
Ernst, Alexandra
;
Waltinger, Ulli
Department:
Center of Excellence - Cognitive Interaction Technology CITEC
Technische Fakultät
X1 - Multimodal alignment corpora: ...
Technische Fakultät
X1 - Multimodal alignment corpora: ...
PUB-ID:
1904067 | Link: http://pub.uni-bielefeld.de/publication/1904067
Who Is It? Context Sensitive Named Entity and Instance Recognition by Means of Wikipedia
Waltinger U, Mehler A (2008)
In: Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence (WI-2008). 1. Los Alamitos, CA, USA: IEEE Computer Society: 381 - 384.
In: Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence (WI-2008). 1. Los Alamitos, CA, USA: IEEE Computer Society: 381 - 384.
Download:
Conference Proceeding/Paper
|
Published
|
English
Authors:
Waltinger, Ulli
;
Mehler, Alexander
Department:
Center of Excellence - Cognitive Interaction Technology CITEC
Technische Fakultät
X1 - Multimodal alignment corpora: ...
Technische Fakultät
X1 - Multimodal alignment corpora: ...
ISBN:
978-0-7695-3496-1
PUB-ID:
1904064 | Link: http://pub.uni-bielefeld.de/publication/1904064
Structural similarities of complex networks: A computational model by example of wiki graphs
Mehler A (2008)
Applied Artificial Intelligence 22(7-8): 619 - 683.
Applied Artificial Intelligence 22(7-8): 619 - 683.
Download:
Journal Article
|
Published
|
English
Authors:
Mehler, Alexander
Department:
Center of Excellence - Cognitive Interaction Technology CITEC
A3 - Dialogue and group dynamics
X1 - Multimodal alignment corpora: ...
Technische Fakultät
A3 - Dialogue and group dynamics
X1 - Multimodal alignment corpora: ...
Technische Fakultät
Abstract:
This article elaborates a framework for representing and classifying large complex networks by example of wiki graphs. By means of this framework we reliably measure the similarity of document, agent, and word networks by solely regarding their topology. In doing so, the article departs from classical approaches to complex network theory which focuses on topological characteristics in order to check their small world property. This does not only include characteristics that have been studied in complex network theory, but also some of those which were invented in social network analysis and hypertext theory. We show that network classifications come into reach which go beyond the hypertext structures traditionally analyzed in web mining. The reason is that we focus on networks as a whole as units to be classifiedabove the level of websites and their constitutive pages. As a consequence, we bridge classical approaches to text and web mining on the one hand and complex network theory on the other hand. Last but not least, this approach also provides a framework for quantifying the linguistic notion of intertextuality.
This article elaborates a framework for representing and classifying large complex networks by example of wiki graphs. By means of this framework we reliably measure the similarity of document, agent, and word networks by solely regarding their topology. In doing so, the article departs from classical approaches to complex network theory which focuses on topological characteristics in order to check their small world property. This does not only include characteristics that have been studied in complex network theory, but also some of those which were invented in social network analysis and hypertext theory. We show that network classifications come into reach which go beyond the hypertext structures traditionally analyzed in web mining. The reason is that we focus on networks as a whole as units to be classifiedabove the level of websites and their constitutive pages. As a consequence, we bridge classical approaches to text and web mining on the one hand and complex network theory on the other hand. Last but not least, this approach also provides a framework for quantifying the linguistic notion of intertextuality.
ISSN:
0883-9514
PUB-ID:
1586527 | Link: http://pub.uni-bielefeld.de/publication/1586527
New CITEC Building
Interactive Intelligent Systems
Funded in the Excellence-Initiative
