Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Hybrid Recommender Systems: Survey and Experiments
User Modeling and User-Adapted Interaction
eResponder: Electronic Question Responder
CooplS '02 Proceedings of the 7th International Conference on Cooperative Information Systems
Statistical and Inductive Inference by Minimum Message Length (Information Science and Statistics)
Statistical and Inductive Inference by Minimum Message Length (Information Science and Statistics)
In question answering, two heads are better than one
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Query-relevant summarization using FAQs
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
A hybrid approach for improving predictive accuracy of collaborative filtering algorithms
User Modeling and User-Adapted Interaction
A predictive approach to help-desk response generation
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A comparative study of information-gathering approaches for answering help-desk email inquiries
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Cross-disciplinary perspectives on meta-learning for algorithm selection
ACM Computing Surveys (CSUR)
An empirical study of corpus-based response automation methods for an e-mail-based help-desk domain
Computational Linguistics
Hi-index | 0.00 |
We present a corpus-based approach for the automation of help-desk responses to users' email requests. Automation is performed on the basis of the similarity between a request and previous requests, which affects both the content included in a response and the strategy used to produce it. The latter is the focus of this paper, which introduces a meta-learning mechanism that selects between different information-gathering strategies, such as document retrieval and multidocument summarization. Our results show that this mechanism outperforms a random strategy-selection policy, and performs competitively with a gold baseline that always selects the best strategy.