Utterance Intent Classification for Spoken Dialogue System with Data-Driven Untying of Recursive Autoencoders

Tsuneo KATO  Atsushi NAGAI  Naoki NODA  Jianming WU  Seiichi YAMAMOTO  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D    No.6    pp.1197-1205
Publication Date: 2019/06/01
Publicized: 2019/03/04
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDP7319
Type of Manuscript: PAPER
Category: Natural Language Processing
utterance intent classification,  spoken dialogue system,  recursive autoencoder,  data-driven untying,  

Full Text: FreePDF(972.8KB)

Data-driven untying of a recursive autoencoder (RAE) is proposed for utterance intent classification for spoken dialogue systems. Although an RAE expresses a nonlinear operation on two neighboring child nodes in a parse tree in the application of spoken language understanding (SLU) of spoken dialogue systems, the nonlinear operation is considered to be intrinsically different depending on the types of child nodes. To reduce the gap between the single nonlinear operation of an RAE and intrinsically different operations depending on the node types, a data-driven untying of autoencoders using part-of-speech (PoS) tags at leaf nodes is proposed. When using the proposed method, the experimental results on two corpora: ATIS English data set and Japanese data set of a smartphone-based spoken dialogue system showed improved accuracies compared to when using the tied RAE, as well as a reasonable difference in untying between two languages.

open access publishing via