TY - CHAP
T1 - Transfer Learning for Unseen Slots in End-to-End Dialogue State Tracking
AU - Iwata, Kenji
AU - Yoshida, Takami
AU - Fujimura, Hiroshi
AU - Akamine, Masami
N1 - Publisher Copyright:
© 2020, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - This paper proposes a transfer learning algorithm for end-to-end dialogue state tracking (DST) to handle new slots with a small set of training data, which has not yet been discussed in the literature on conventional approaches. The goal of transfer learning is to improve DST performance for new slots by leveraging slot-independent parameters extracted from DST models for existing slots. An end-to-end DST model is composed of a spoken language understanding module and an update module. We assume that parameters of the update module can be slot-independent. To make the parameters slot-independent, a DST model for each existing slot is trained by sharing the parameters of the update module across all existing slots. The slot-independent parameters are transferred to a DST model for the new slot. Experimental results show that the proposed algorithm achieves 82.5% accuracy on the DSTC2 dataset, outperforming a baseline algorithm by 1.8% when applied to a small set of training data. We also show its potential robustness for the network architecture of update modules.
AB - This paper proposes a transfer learning algorithm for end-to-end dialogue state tracking (DST) to handle new slots with a small set of training data, which has not yet been discussed in the literature on conventional approaches. The goal of transfer learning is to improve DST performance for new slots by leveraging slot-independent parameters extracted from DST models for existing slots. An end-to-end DST model is composed of a spoken language understanding module and an update module. We assume that parameters of the update module can be slot-independent. To make the parameters slot-independent, a DST model for each existing slot is trained by sharing the parameters of the update module across all existing slots. The slot-independent parameters are transferred to a DST model for the new slot. Experimental results show that the proposed algorithm achieves 82.5% accuracy on the DSTC2 dataset, outperforming a baseline algorithm by 1.8% when applied to a small set of training data. We also show its potential robustness for the network architecture of update modules.
UR - http://www.scopus.com/inward/record.url?scp=85102621029&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102621029&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-9323-9_5
DO - 10.1007/978-981-15-9323-9_5
M3 - Chapter
AN - SCOPUS:85102621029
T3 - Lecture Notes in Electrical Engineering
SP - 53
EP - 65
BT - Lecture Notes in Electrical Engineering
PB - Springer Science and Business Media Deutschland GmbH
ER -