Abstract
Automated answering of frequent email inquiries is a text categorization task with narrow text categories, where all messages in one text category have the same answer. Such email categorization is optimized for high precision and at least acceptable recall. We tested matching of surface text patterns to nearly ten thousand email messages and achieved around 90 % precision; the corresponding recall figures were 45–75 % in different text categories. In order to achieve this performance level, the text patterns are designed to identify both the context of an email inquiry and the actual need that has created the inquiry—a question, request, or complaint. Our error analysis has pinpointed 12 reasons why text pattern matching may fail.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Downey, D., Etzioni, O., Soderland, S., Weld, D.S.: Learning text patterns for web information extraction and assessment. In: Proc. AAAI-04 workshop on adaptive text extraction and mining, pp. 50-55 (2004)
Sneiders, E.: Automated FAQ Answering with Question-Specific Knowledge Representa-tion for Web Self-Service. In: Proc. 2nd International Conference on Human System Inter-action (HSI’09), May 21-23, Catania, Italy, pp.298-305, IEEE (2009)
Sneiders, E.: Automated Email Answering by Text Pattern Matching. In: H. Loftsson, E. Rögnvaldsson, S. Helgadóttir (eds.): Proc. 7th International Conference on Natural Language Processing (IceTAL), August 16-18, Reykjavik, Iceland, LNAI 6233, pp. 381-392. Springer, Heidelberg (2010)
Kosseim, L., Beauregard, S., Lapalme, G.: Using information extraction and natural language generation to answer e-mail. Data & Knowledge Engineering, vol. 38, pp. 85-100 (2001)
Khosravi, H., Wilks, Y.: Routing email automatically by purpose not topic. Natural Language Engineering, 5, pp. 237-250 (1999)
Corston-Oliver, S., Ringger, E., Gamon, M., Campbell, R.: Task-focused summarization of email. In: Proc. ACL-04 Workshop: Text Summarization Branches Out, pp. 43-50 (2004)
Lampert, A., Dale, R., Paris, C.: The nature of requests and commitments in email messages. In: Proc. of the AAAI Workshop on Enhanced Messaging, pp. 42-47 (2008)
Lampert, A., Dale, R., Paris, C.: Requests and Commitments in Email are More Complex Than You Think: Eight Reasons to be Cautious. In: Proc. Australasian Language Technology Association Workshop, vol. 6, pp. 64-72 (2008)
Goldstein, J., Sabin, R.E.: Using speech acts to categorize email and identify email genres. In: Proc. 39th Annual Hawaii International Conference on System Sciences, vol. 3. IEEE (2006)
Dalianis, H., Sjöbergh, J., Sneiders, E.: Comparing manual text patterns and machine learning for classification of e-mails for automatic answering by a government agency. In: Proc. Computational Linguistics and Intelligent Text Processing, pp. 234-243. Springer Berlin Heidelberg. (2011)
Sneiders, E.: Automated FAQ Answering: Continued Experience with Shallow Language Understanding. In: Question Answering Systems. Papers from the 1999 AAAI Fall Symposium. Technical Report FS-99-02, November 5-7, North Falmouth, Massachusetts, USA. AAAI Press, pp.97-107(1999)
Sneiders, E., Eriksson, G., Alfalahi, A.: Exploring the Traits of Manual E-Mail Categorization Text Patterns. In: Advances in Natural Language Processing, pp. 337-344. Springer International Publishing (2015)
Tang, G., Pei, J., Luk, W. S.:. Email mining: tasks, common techniques, and tools. Knowledge and Information Systems, 41(1), 1-31 (2014)
Everitt, B.: The Analysis of Contingency Tables. Chapman & Hall, London (1977)
Sneiders, E.: Review of the Main Approaches to Automated Email Answering. In: Proc. WorldCist’16, Recife, Brazil, March 22-24. Springer International Publishing (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Sneiders, E., Sjöbergh, J., Alfalahi, A. (2016). Email Answering by Matching Question and Context-Specific Text Patterns: Performance and Error Analysis. In: Rocha, Á., Correia, A., Adeli, H., Reis, L., Mendonça Teixeira, M. (eds) New Advances in Information Systems and Technologies. Advances in Intelligent Systems and Computing, vol 444. Springer, Cham. https://doi.org/10.1007/978-3-319-31232-3_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-31232-3_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-31231-6
Online ISBN: 978-3-319-31232-3
eBook Packages: EngineeringEngineering (R0)