A Meta-Learning Approach for Selecting Between Response Automation Strategies in a Help-Desk Domain

Abstract

We present a corpus-based approach for the automation of help-desk responses to users ’ email requests. Au-tomation is performed on the basis of the similarity be-tween 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 pa-per, which introduces a meta-learning mechanism that selects between different information-gathering strate-gies, such as document retrieval and multi-document 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.

Cite

Text

Marom et al. "A Meta-Learning Approach for Selecting Between Response Automation Strategies in a Help-Desk Domain." AAAI Conference on Artificial Intelligence, 2007.

Markdown

[Marom et al. "A Meta-Learning Approach for Selecting Between Response Automation Strategies in a Help-Desk Domain." AAAI Conference on Artificial Intelligence, 2007.](https://mlanthology.org/aaai/2007/marom2007aaai-meta/)

BibTeX

@inproceedings{marom2007aaai-meta,
  title     = {{A Meta-Learning Approach for Selecting Between Response Automation Strategies in a Help-Desk Domain}},
  author    = {Marom, Yuval and Zukerman, Ingrid and Japkowicz, Nathalie},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2007},
  pages     = {907-912},
  url       = {https://mlanthology.org/aaai/2007/marom2007aaai-meta/}
}