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.
CITATION STYLE
Kato, T., Nagai, A., Noda, N., Sumitomo, R., Wu, J., & Yamamoto, S. (2017). Utterance intent classification of a spoken dialogue system with efficiently untied recursive autoencoders. In SIGDIAL 2017 - 18th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference (pp. 60–64). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w17-5508
Mendeley helps you to discover research relevant for your work.