Utterance Intent Classification of a Spoken Dialogue System with Efficiently Untied Recursive Autoencoders

Tsuneo Kato, Atsushi Nagai, Naoki Noda, Ryosuke Sumitomo, Jianming Wu, Seiichi Yamamoto


Abstract
Recursive autoencoders (RAEs) for compositionality of a vector space model were applied to utterance intent classification of a smartphone-based Japanese-language spoken dialogue system. Though the RAEs express a nonlinear operation on the vectors of child nodes, the operation is considered to be different intrinsically depending on types of child nodes. To relax the difference, a data-driven untying of autoencoders (AEs) is proposed. The experimental result of the utterance intent classification showed an improved accuracy with the proposed method compared with the basic tied RAE and untied RAE based on a manual rule.
Anthology ID:
W17-5508
Volume:
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
Month:
August
Year:
2017
Address:
Saarbrücken, Germany
Venues:
SIGDIAL | WS
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
60–64
URL:
https://www.aclweb.org/anthology/W17-5508
DOI:
10.18653/v1/W17-5508
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/W17-5508.pdf