Dialogue Breakdown Detection with Long Short Term Memory

Tittaya Mairittha; Tsuyoshi Okita; Sozo Inoue

Mobile Computing, Applications, and Services. 9th International Conference, MobiCASE 2018, Osaka, Japan, February 28 – March 2, 2018, Proceedings

Research Article

Dialogue Breakdown Detection with Long Short Term Memory

Download

149 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-90740-6_18,
    author={Tittaya Mairittha and Tsuyoshi Okita and Sozo Inoue},
    title={Dialogue Breakdown Detection with Long Short Term Memory},
    proceedings={Mobile Computing, Applications, and Services. 9th International Conference, MobiCASE 2018,  Osaka, Japan, February 28 -- March 2, 2018, Proceedings},
    proceedings_a={MOBICASE},
    year={2018},
    month={5},
    keywords={Dialogue breakdown Dialogue systems Text classification},
    doi={10.1007/978-3-319-90740-6_18}
}

Tittaya Mairittha
Tsuyoshi Okita
Sozo Inoue
Year: 2018
Dialogue Breakdown Detection with Long Short Term Memory
MOBICASE
Springer
DOI: 10.1007/978-3-319-90740-6_18

Tittaya Mairittha¹^,*, Tsuyoshi Okita¹^,*, Sozo Inoue¹^,*

1: Kyushu Institute of Technology

*Contact email: fon@sozolab.jp, okita@sozolab.jp, sozo@sozolab.jp

Abstract

This paper aims to detect the utterance which can be categorized as the breakdown of the dialogue flow. We propose a logistic regression-based and a Long Short-Term Memory (LSTM)-based methods. Using the input with utterance-response pairs, the performance of the LSTM-based method is superior to that of the logistic regression-based method in 36% measured with F-measure. We also measured the performance using the performance with utterance-response pairs: the performance with the input only with responses is unexpectedly inferior to those with responses in 6% to 23% measured with F-measure.

Keywords: Dialogue breakdown Dialogue systems Text classification

Published: 2018-05-11
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-90740-6_18