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
  • [31] Discriminative Reranking for Spoken Language Understanding
    Dinarelli, Marco
    Moschitti, Alessandro
    Riccardi, Giuseppe
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (02): : 526 - 539
  • [32] TEMPORAL STRUCTURE OF SPOKEN LANGUAGE UNDERSTANDING
    MARSLENWILSON, W
    TYLER, LK
    COGNITION, 1980, 8 (01) : 1 - 71
  • [33] Active learning for spoken language understanding
    Tur, G
    Schapire, RE
    Hakkani-Tür, D
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING I, 2003, : 276 - 279
  • [34] SENTENCE SIMPLIFICATION FOR SPOKEN LANGUAGE UNDERSTANDING
    Tur, Gokhan
    Hakkani-Tuer, Dilek
    Heck, Larry
    Parthasarathy, S.
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5628 - 5631
  • [35] Temporal Generalization for Spoken Language Understanding
    Gaspers, Judith
    Kumar, Anoop
    Ver Steeg, Greg
    Galstyan, Aram
    Ai, Amazon Alexa
    2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, NAACL-HLT 2022, 2022, : 37 - 44
  • [36] Model adaptation for spoken language understanding
    Tur, G
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 41 - 44
  • [37] Grammar learning for spoken language understanding
    Wang, YY
    Acero, A
    ASRU 2001: IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, CONFERENCE PROCEEDINGS, 2001, : 292 - 295
  • [38] UNDERSTANDING SPOKEN LANGUAGE - WALKER,DE
    IIVONEN, A
    COMPUTERS AND THE HUMANITIES, 1982, 16 (01): : 45 - 47
  • [39] A mixed approach to spoken language understanding
    Liu, JY
    Wang, C
    Proceedings of the 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE'05), 2005, : 169 - 173
  • [40] Chinese spoken language understanding in SHTQS
    毛家菊
    郭荣
    陆汝占
    Journal of Harbin Institute of Technology, 2005, (02) : 225 - 230