Semantics- and Emotion-Based Conversation Management in Customer Support (SIGMUND)



Customer Relationship Management (CRM), call center systems and their strategic integration plays a major role in the organisation of efficient customer service and contact. This integration requires the quick and efficient access of information, as in a telephone conversation customer-related data has to be available in real-time.


For the outbound telephony usually a certain amount of support is availabe in CRM systems (e.g. campaign management), however for incoming calls there is only minimal support available - mostly based on the telephone number of the caller. Providing context-relevant information would be an outstanding step to optimise telephone-bound customer processes.



SIGMUND is expected to open a completely new area of situation-based support for telephone-bound conversation: real-time support for the agent / consultant by automatically monitoring conversations; retrieval and presentation of information relevant to the context .


System Architecture

SIGMUND addresses the new field of context-sensitive support for call centers. Research and development focuses on real-time support for the call center agent: the ongoing conversation is automatically monitored and relevant information is selected and presented within the context of the conversation. Therefore, the efficiency of consultation largely improves.


SIGMUND focuses on two highly innovative and research-oriented areas:


  • The application recognizes customer behaviour and the topic of the conversation by automatically analyzing the speech and presenting resulting hypotheses during the conversation.
  • Semantically enriched CRM data relevant to the context is retrieved and displayed to support the agent during the consultation. The semantic content is extracted using advanced Information Retrieval and Text Mining methods


The SIGMUND project develops applied prototypes in these innovative research areas and aims to completely integrate language and knowledge engineering and call center management to support consultants / agents.


For further information, you can also visit the SIGMUND project homepage.



Overview of the SIGMUND Architecture

Project Publications

Additional Attributes


Combining heterogeneous knowledge resources for improved distributional semantic models

György Szarvas, Torsten Zesch, Iryna Gurevych
In: Proceedings of the 12th International Conference on Intelligent Text Processing and Computational Linguistics, Vol. 6608, p. 289--303, 2011

Combining query translation techniques to improve cross-language information retrieval

Benjamin Herbert, György Szarvas, Iryna Gurevych
In: Proceedings of the 33rd European Conference on Information Retrieval, Vol. 6611, p. 712-715, 2011

TUD: semantic relatedness for relation classification

György Szarvas, Iryna Gurevych
In: Proceedings of the 5th ACL SIGLEX Workshop on Semantic Evaluation, p. 210--213, July 2010
[Online-Edition: 2907]

Prior Art Search Using International Patent Classification Codes and All-Claims-Queries

Benjamin Herbert, György Szarvas, Iryna Gurevych
In: CLEF 2009 Workshop, Part I, Vol. 6241, p. 712--715, 2010

Prior Art Search using International Patent Classification Codes and All-Claims-Queries

György Szarvas, Benjamin Herbert, Iryna Gurevych
In: Working Notes of the 10th Workshop of the Cross Language Evaluation Forum (CLEF), August 2009

Integrating Semantic Knowledge into Text Similarity and Information Retrieval

Christof Müller, Iryna Gurevych, Max Mühlhäuser
In: Proceedings of the First IEEE International Conference on Semantic Computing (ICSC), p. 257-264, 2007

Exploring the Potential of Semantic Relatedness in Information Retrieval

Christof Müller, Iryna Gurevych
In: LWA 2006 Lernen - Wissensentdeckung - Adaptivität, 9.-11.10.2006 in Hildesheim, p. 126-131, October 2006
Universität Hildesheim





The project is funded by the German Ministry of Education and Research (BMBF) as part of the Call "SME-innovations: Information- and Communikation Technologies (ICT)" - Software Systems and Knowledge Processing.

A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang