Proceedings

A Predictive Approach to Help-Desk Response Generation

Download BibTeX Cite

Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 1665-1669.

© 2007 International Joint Conferences on Artificial Intelligence

Abstract

We are developing a corpus-based approach for the prediction of help-desk responses from features in customers' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic and human-based evaluation of our system's responses. The automatic evaluation involves textual comparisons between generated responses and responses composed by help-desk operators. Our results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.

  1. [Berger and Mittal, 2000] A. Berger and V.O. Mittal. Query- relevant summarization using FAQs. In Proc. of the 38th Annual Meeting of the Association for Computational Lin- guistics (ACL'00), pages 294-301, Hong Kong, 2000.
  2. [Bickel and Scheffer, 2004] S. Bickel and T. Scheffer. Learn- ing from message pairs for automatic email answering. In Proc. of the European Conference on Machine Learning (ECML'04), Pisa, Italy, 2004.
  3. [Carmel et al., 2000] D. Carmel, M. Shtalhaim, and A. Sof- fer. eResponder: Electronic question responder. In Proc. of the 7th International Conference on Cooperative Infor- mation Systems, pages 150-161, Eilat, Israel, 2000.
  4. [Filatova and Hatzivassiloglou, 2004] E. Filatova and V. Hatzivassiloglou. A formal model for information selection in multi-sentence text extraction. In Proc. of the 20th International Conference on Computational Linguis- tics (COLING'04), pages 397-403, Geneva, Switzerland, 2004.
  5. [Lin and Hovy, 2003] C.Y. Lin and E.H. Hovy. Automatic evaluation of summaries using n-gram co-occurrence statistics. In Proc. of the 2003 Language Technology Con- ference (HLT-NAACL'03), Edmonton, Canada, 2003.
  6. [Marom and Zukerman, 2005] Y. Marom and I. Zukerman. Corpus-based generation of easy help-desk responses. Technical Report 2005/166, School of Computer Science and Software Engineering, Monash University, Clayton, Australia, 2005.
  7. [Oliver, 1993] J.J. Oliver. Decision graphs -an extension of decision trees. In Proc. of the Fourth International Work- shop on Artificial Intelligence and Statistics, pages 343- 350, Fort Lauderdale, Florida, 1993.
  8. [Pedersen et al., 2004] T. Pedersen, S. Patwardhan, and J. Michelizzi. WordNet::Similarity -measuring the relat- edness of concepts. In Proc. of the Nineteenth National Conference on Artificial Intelligence (AAAI'04), pages 25- 29, San Jose, California, 2004.
  9. [Salton and McGill, 1983] G. Salton and M.J. McGill. An Introduction to Modern Information Retrieval. McGraw Hill, 1983.
  10. [Wallace and Boulton, 1968] C.S. Wallace and D.M. Boul- ton. An information measure for classification. The Com- puter Journal, 11(2):185-194, 1968.
  11. [Zukerman and Marom, 2006] I. Zukerman and Y. Marom. A comparative study of information-gathering approaches for answering help-desk email inquiries. In Proc. of the 19th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, 2006.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards