A Predictive Approach to Help-Desk Response Generation

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.

Cite

Text

Marom and Zukerman. "A Predictive Approach to Help-Desk Response Generation." International Joint Conference on Artificial Intelligence, 2007.

Markdown

[Marom and Zukerman. "A Predictive Approach to Help-Desk Response Generation." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/marom2007ijcai-predictive/)

BibTeX

@inproceedings{marom2007ijcai-predictive,
  title     = {{A Predictive Approach to Help-Desk Response Generation}},
  author    = {Marom, Yuval and Zukerman, Ingrid},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2007},
  pages     = {1665-1670},
  url       = {https://mlanthology.org/ijcai/2007/marom2007ijcai-predictive/}
}