Publication

Efficient learning of email similarities for customer support

Bakker, J. & Bunte, K., 24-Apr-2019, 27th European Symposium on Artificial Neural Networks, ESANN 2019. Verleysen, M. (ed.). d-side publishing, p. 119-124 6 p.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

APA

Bakker, J., & Bunte, K. (2019). Efficient learning of email similarities for customer support. In M. Verleysen (Ed.), 27th European Symposium on Artificial Neural Networks, ESANN 2019 (pp. 119-124). d-side publishing.

Author

Bakker, Jelle ; Bunte, Kerstin. / Efficient learning of email similarities for customer support. 27th European Symposium on Artificial Neural Networks, ESANN 2019. editor / Michel Verleysen. d-side publishing, 2019. pp. 119-124

Harvard

Bakker, J & Bunte, K 2019, Efficient learning of email similarities for customer support. in M Verleysen (ed.), 27th European Symposium on Artificial Neural Networks, ESANN 2019. d-side publishing, pp. 119-124, The 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
, Bruges , Belgium, 24/04/2019.

Standard

Efficient learning of email similarities for customer support. / Bakker, Jelle; Bunte, Kerstin.

27th European Symposium on Artificial Neural Networks, ESANN 2019. ed. / Michel Verleysen. d-side publishing, 2019. p. 119-124.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Vancouver

Bakker J, Bunte K. Efficient learning of email similarities for customer support. In Verleysen M, editor, 27th European Symposium on Artificial Neural Networks, ESANN 2019. d-side publishing. 2019. p. 119-124


BibTeX

@inproceedings{a5a8bbc127c046fb87af943f52226704,
title = "Efficient learning of email similarities for customer support",
abstract = "One way to increase customer satisfaction is efficient and consistent customer email support. In this contribution we investigate the useof dimensionality reduction, metric learning and classification methods topredict answer templates that can be used by an employee or retrieve historic conversations with potential suitable answers given an email query.The strategies are tested on email data and the publicly available Reutersdata. We conclude that prototype-based metric learning is fast to trainand the parameters provide a compressed representation of the databaseenabling efficient content based retrieval. Furthermore, learning customeremail embedings based on the similarity of employee answers is a promising direction for computer aided customer support.",
author = "Jelle Bakker and Kerstin Bunte",
year = "2019",
month = "4",
day = "24",
language = "English",
isbn = "978-287-587-065-0",
pages = "119--124",
editor = "Michel Verleysen",
booktitle = "27th European Symposium on Artificial Neural Networks, ESANN 2019",
publisher = "d-side publishing",

}

RIS

TY - GEN

T1 - Efficient learning of email similarities for customer support

AU - Bakker, Jelle

AU - Bunte, Kerstin

PY - 2019/4/24

Y1 - 2019/4/24

N2 - One way to increase customer satisfaction is efficient and consistent customer email support. In this contribution we investigate the useof dimensionality reduction, metric learning and classification methods topredict answer templates that can be used by an employee or retrieve historic conversations with potential suitable answers given an email query.The strategies are tested on email data and the publicly available Reutersdata. We conclude that prototype-based metric learning is fast to trainand the parameters provide a compressed representation of the databaseenabling efficient content based retrieval. Furthermore, learning customeremail embedings based on the similarity of employee answers is a promising direction for computer aided customer support.

AB - One way to increase customer satisfaction is efficient and consistent customer email support. In this contribution we investigate the useof dimensionality reduction, metric learning and classification methods topredict answer templates that can be used by an employee or retrieve historic conversations with potential suitable answers given an email query.The strategies are tested on email data and the publicly available Reutersdata. We conclude that prototype-based metric learning is fast to trainand the parameters provide a compressed representation of the databaseenabling efficient content based retrieval. Furthermore, learning customeremail embedings based on the similarity of employee answers is a promising direction for computer aided customer support.

M3 - Conference contribution

SN - 978-287-587-065-0

SP - 119

EP - 124

BT - 27th European Symposium on Artificial Neural Networks, ESANN 2019

A2 - Verleysen, Michel

PB - d-side publishing

ER -

ID: 83292533