Shadow Answers as an Intermediary in Email Answer Retrieval
A set of standard answers facilitates answering emails at customer care centers. Matching the text of user emails to the standard answers may not be productive because they do not necessarily have the same wording. Therefore we examine archived email-answer pairs and establish query-answer term co-occurrences. When a new user email arrives, we replace query words with most co-occurring answer words and obtain a “shadow answer”, which is a new query to retrieve standard answers. As a measure of term co-occurrence strength we test raw term co-occurrences and Pointwise Mutual Information.
KeywordsEmail answering Statistical word associations Shadow answer
Unable to display preview. Download preview PDF.
- 2.Lapalme, G., Kosseim, L.: Mercure: Towards an automatic e-mail follow-up system. IEEE Computational Intelligence Bulletin 2(1), 14–18 (2003). IEEEGoogle Scholar
- 3.Itakura, K., Kenmotsu, M., Oka, H., Akiyoshi, M.: An identification method of inquiry e-mails to the matching FAQ for automatic question answering. In: Distributed Computing and Artificial Intelligence, pp. 213–219. Springer, Heidelberg (2010)Google Scholar
- 4.Marom, Y., Zukerman, I.: Towards a framework for collating help-desk responses from multiple documents. In: Proceedings of the IJCAI05 Workshop on Knowledge and Reasoning for Answering Questions, pp. 32–39 (2005)Google Scholar
- 5.Malik, R., Subramaniam, L.V., Kaushik, S.: Automatically selecting answer templates to respond to customer emails. In: IJCAI, vol. 7, pp. 1659–1664 (2007)Google Scholar
- 6.Lamontagne, L., Langlais, P., Lapalme, G.: Using statistical word associations for the retrieval of strongly-textual cases. In: FLAIRS Conference, pp. 124–128 (2003)Google Scholar
- 7.Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: ICML, vol. 97, pp. 412–420 (1997)Google Scholar