Abstract
With the complexity of systems increasing, support centers are flooded with questions submitted by e-mail, by Web, or by phone. This paper describes eResponder, a system which provides an integrated solution for automatic responses to user questions. eResponder stores question and answer pairs that have previously been asked. These pairs can be used to either provide an immediate response to user questions, or to assist customer service representatives in drafting new responses to similar questions or to yet unanswered questions. Users submit free text questions to the system via one unified interface. When a new question arrives, the system searches its databases for similar questions as well as for relevant answers and finds the most relevant Q&A pair based on both these measures. eResponder provides a relevance feedback mechanism and an answer summarizer to assist CSR’s in creating new responses. The results of an experiment conducted to evaluate the system performance show that the combination of independent question and answer scores yields high precision search results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
2000 Microsoft Corporation. Microsoft product support service. http://support.microsoft.com/directory
Fischetti, M.: Ending Email overload. IBM Research (1@2), 33–37 (1998)
The National Science Foundation. Ask a scientist or engineer. http://www.nsf.gov/nstwquestions/start.html
2000 Electronic Arts Inc. Easports clubhouse. http://www.easports.com/clubhouse.cfm
Maarek, Y., Smadja, F.: Full text indexing based on lexical relations, an application: Software libraries. In: Belkin, N., van Rijsbergen, C. (eds.) Proceedings of the twelfth annual international ACM SIGIR conference on Research and development in information retrieval, pp. 198–206. ACM press, Cambridge (1989)
Rocchio, J.J.: Relevance feedback in information retrieval. In: The SMART Retrieval System: Experiments in Automatic Document Processing, pp. 313–323. Prentice-Hall Inc, Englewood Cliffs (1971)
Sanderson, M.: Accurate user directed summarization from existing tools. In: Proceedings of the 1998 ACM 7th international conference on Information and knowledge management, Washington, United States, pp. 45–51 (1998)
Schechter, B.: Driving eBuisiness. IBM Research (4) (1999)
Voorhees, E.M., Tice, D.: The TREC-8 question answering track evaluation. In: NIST Special Publication XXX-XXX: The Eighth Text REtrieval Conference (TREC 8), August 1999. National Institute of Standards and Technology (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carmel, D., Shtalhaim, M., Soffer, A. (2000). eResponder: Electronic Question Responder. In: Scheuermann, P., Etzion, O. (eds) Cooperative Information Systems. CoopIS 2000. Lecture Notes in Computer Science, vol 1901. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10722620_16
Download citation
DOI: https://doi.org/10.1007/10722620_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41021-8
Online ISBN: 978-3-540-45266-9
eBook Packages: Springer Book Archive