Dual Learning for Semi-Supervised Natural Language Understanding

被引:22
|
作者
Zhu, Su [1 ,2 ]
Cao, Ruisheng [1 ,2 ]
Yu, Kai [1 ,2 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, AI Inst, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, MoE Key Lab Artificial Intelligence, AI Inst, Shanghai 200240, Peoples R China
关键词
Task analysis; Semantics; Natural languages; Supervised learning; Neural networks; Annotations; Speech processing; Natural language understanding (NLU); semi-supervised learning; dual learning; slot filling; intent detection; RECURRENT NEURAL-NETWORKS; MODELS;
D O I
10.1109/TASLP.2020.3001684
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Natural language understanding (NLU) converts sentences into structured semantic forms. The paucity of annotated training samples is still a fundamental challenge of NLU. To solve this data sparsity problem, previous work based on semi-supervised learning mainly focuses on exploiting unlabeled sentences. In this work, we introduce a dual task of NLU, semantic-to-sentence generation (SSG), and propose a new framework for semi-supervised NLU with the corresponding dual model. The framework is composed of dual pseudo-labeling and dual learning method, which enables an NLU model to make full use of data (labeled and unlabeled) through a closed-loop of the primal and dual tasks. By incorporating the dual task, the framework can exploit pure semantic forms as well as unlabeled sentences, and further improve the NLU and SSG models iteratively in the closed-loop. The proposed approaches are evaluated on two public datasets (ATIS and SNIPS). Experiments in the semi-supervised setting show that our methods can outperform various baselines significantly, and extensive ablation studies are conducted to verify the effectiveness of our framework. Finally, our method can also achieve the state-of-the-art performance on the two datasets in the supervised setting.
引用
收藏
页码:1936 / 1947
页数:12
相关论文
共 50 条
  • [1] Semi-Supervised Learning of Statistical Models for Natural Language Understanding
    Zhou, Deyu
    He, Yulan
    [J]. SCIENTIFIC WORLD JOURNAL, 2014,
  • [2] Industry Scale Semi-Supervised Learning for Natural Language Understanding
    Chen, Luoxin
    Garcia, Francisco
    Kumar, Varun
    Xie, He
    Lu, Jianhua
    [J]. 2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, NAACL-HLT 2021, 2021, : 311 - 318
  • [3] EFFICIENT SEMI-SUPERVISED LEARNING FOR NATURAL LANGUAGE UNDERSTANDING BY OPTIMIZING DIVERSITY
    Cho, Eunah
    Xie, He
    Lalor, John P.
    Kumar, Varun
    Campbell, William M.
    [J]. 2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), 2019, : 1077 - 1084
  • [4] Efficient Semi-supervised Consistency Training for Natural Language Understanding
    Leung, George
    Tan, Joshua
    [J]. 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, NAACL-HLT 2022, 2022, : 86 - 93
  • [5] Combining active and semi-supervised learning for spoken language understanding
    Tur, G
    Hakkani-Tür, D
    Schapire, RE
    [J]. SPEECH COMMUNICATION, 2005, 45 (02) : 171 - 186
  • [6] A semi-supervised learning method for semantic modeling in language understanding
    Ortega, L.
    Galiano, I.
    Hurtado, L. F.
    Sanchis, E.
    Segarra, E.
    [J]. PROCESAMIENTO DEL LENGUAJE NATURAL, 2010, (45): : 199 - 205
  • [8] Semi-Supervised Learning and Domain Adaptation in Natural Language Processing
    Foster, George
    [J]. COMPUTATIONAL LINGUISTICS, 2014, 40 (02) : 519 - 522
  • [9] Semi-Supervised Learning and Domain Adaptation in Natural Language Processing
    Lefevre, Fabrice
    [J]. TRAITEMENT AUTOMATIQUE DES LANGUES, 2013, 54 (01): : 235 - 237
  • [10] Dual Supervised Learning for Natural Language Understanding and Generation
    Su, Shang-Yu
    Huang, Chao-Wei
    Chen, Yun-Nung
    [J]. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 5472 - 5477