Learning from Message Pairs for Automatic Email Answering

Abstract

We consider the problem of learning a mapping from question to answer messages. The training data for this problem consist of pairs of messages that have been received and sent in the past. We formulate the problem setting, discuss appropriate performance metrics, develop a solution and describe two baseline methods for comparison. We present a case study based on emails received and answered by the service center of a large online store.

Cite

Text

Bickel and Scheffer. "Learning from Message Pairs for Automatic Email Answering." European Conference on Machine Learning, 2004. doi:10.1007/978-3-540-30115-8_11

Markdown

[Bickel and Scheffer. "Learning from Message Pairs for Automatic Email Answering." European Conference on Machine Learning, 2004.](https://mlanthology.org/ecmlpkdd/2004/bickel2004ecml-learning/) doi:10.1007/978-3-540-30115-8_11

BibTeX

@inproceedings{bickel2004ecml-learning,
  title     = {{Learning from Message Pairs for Automatic Email Answering}},
  author    = {Bickel, Steffen and Scheffer, Tobias},
  booktitle = {European Conference on Machine Learning},
  year      = {2004},
  pages     = {87-98},
  doi       = {10.1007/978-3-540-30115-8_11},
  url       = {https://mlanthology.org/ecmlpkdd/2004/bickel2004ecml-learning/}
}