Capsule Networks for Low Resource Spoken Language Understanding

被引:21
|
作者
Renkens, Vincent [1 ]
Van Hamme, Hugo [1 ]
机构
[1] KULeuven, Dept Elect Engn, ESAT, Kasteelpk Arenberg 10,Bus 2441, B-3001 Leuven, Belgium
关键词
Spoken Language Understanding; Capsule Networks; Deep Learning; Low Resource;
D O I
10.21437/Interspeech.2018-1013
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Designing a spoken language understanding system for command-and-control applications can be challenging because of a wide variety of domains and users or because of a lack of training data. In this paper we discuss a system that learns from scratch from user demonstrations. This method has the advantage that the same system can be used for many domains and users without modifications and that no training data is required prior to deployment. The user is required to train the system, so for a user friendly experience it is crucial to minimize the required amount of data. In this paper we investigate whether a capsule network can make efficient use of the limited amount of available training data. We compare the proposed model to an approach based on Non-negative Matrix Factorisation which is the state-of-the-art in this setting and another deep learning approach that was recently introduced for end-to-end spoken language understanding. We show that the proposed model outperforms the baseline models for three command-and-control applications: controlling a small robot, a vocally guided card game and a home automation task.
引用
收藏
页码:601 / 605
页数:5
相关论文
共 50 条
  • [1] Low resource end-to-end spoken language understanding with capsule networks
    Poncelet, Jakob
    Renkens, Vincent
    Van hamme, Hugo
    COMPUTER SPEECH AND LANGUAGE, 2021, 66
  • [2] MULTITASK LEARNING FOR LOW RESOURCE SPOKEN LANGUAGE UNDERSTANDING
    Meeus, Quentin
    Moens, Marie Francine
    Van Hamme, Hugo
    INTERSPEECH 2022, 2022, : 4073 - 4077
  • [3] Bidirectional Representations for Low-Resource Spoken Language Understanding
    Meeus, Quentin
    Moens, Marie-Francine
    Van Hamme, Hugo
    APPLIED SCIENCES-BASEL, 2023, 13 (20):
  • [4] Meta Auxiliary Learning for Low-resource Spoken Language Understanding
    Gao, Yingying
    Feng, Junlan
    Deng, Chao
    Zhang, Shilei
    INTERSPEECH 2022, 2022, : 2703 - 2707
  • [5] Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
    Wang, Pu
    Van Hamme, Hugo
    INTERSPEECH 2022, 2022, : 1248 - 1252
  • [6] SLURP: A Spoken Language Understanding Resource Package
    Bastianelli, Emanuele
    Vanzo, Andrea
    Swietojanski, Pawel
    Rieser, Verena
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 7252 - 7262
  • [7] End-to-End Spoken Language Understanding: Bootstrapping in Low Resource Scenarios
    Bhosale, Swapnil
    Sheikh, Imran
    Dumpala, Sri Harsha
    Kopparapu, Sunil Kumar
    INTERSPEECH 2019, 2019, : 1188 - 1192
  • [8] QUATERNION NEURAL NETWORKS FOR SPOKEN LANGUAGE UNDERSTANDING
    Parcollet, Titouan
    Morchid, Mohamed
    Bousquet, Pierre-Michel
    Dufour, Richard
    Linares, Georges
    De Mori, Renato
    2016 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2016), 2016, : 362 - 368
  • [9] Large-scale Transfer Learning for Low-resource Spoken Language Understanding
    Jia, Xueli
    Wang, Jianzong
    Zhang, Zhiyong
    Cheng, Ning
    Xiao, Jing
    INTERSPEECH 2020, 2020, : 1555 - 1559
  • [10] DEEP QUATERNION NEURAL NETWORKS FOR SPOKEN LANGUAGE UNDERSTANDING
    Parcollet, Titouan
    Morchid, Mohamed
    Linares, Georges
    2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2017, : 504 - 511