KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation

被引:0
|
作者
Feng, Yuxi [1 ]
Yi, Xiaoyuan [2 ]
Lakshmanan, Laks V. S. [1 ]
Xie, Xing [2 ]
机构
[1] Univ British Columbia, Vancouver, BC, Canada
[2] Microsoft Res Asia, Beijing, Peoples R China
来源
PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023 | 2023年
基金
加拿大自然科学与工程研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Self-training (ST) has come to fruition in language understanding tasks by producing pseudo labels, which reduces the labeling bottleneck of language model fine-tuning. Nevertheless, in facilitating semi-supervised controllable language generation, ST faces two key challenges. First, augmented by self-generated pseudo text, generation models tend to over-exploit the previously learned text distribution, suffering from mode collapse and poor generation diversity. Second, generating pseudo text in each iteration is time-consuming, severely decelerating the training process. In this work, we propose KEST, a novel and efficient self-training framework to handle these problems. KEST utilizes a kernel-based loss, rather than standard cross entropy, to learn from the soft pseudo text produced by a shared non-autoregressive generator. We demonstrate both theoretically and empirically that KEST can benefit from more diverse pseudo text in an efficient manner, which allows not only refining and exploiting the previously fitted distribution but also enhanced exploration towards a larger potential text space, providing a guarantee of improved performance. Experiments on three controllable generation tasks demonstrate that KEST significantly improves control accuracy while maintaining comparable text fluency and generation diversity against several strong baselines.
引用
收藏
页码:5049 / 5057
页数:9
相关论文
共 50 条
  • [31] Uncertainty-aware Self-training for Few-shot Text Classification
    Mukherjee, Subhabrata
    Awadallah, Ahmed Hassan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [32] Improving Controllable Text Generation with Position-Aware Weighted Decoding
    Gu, Yuxuan
    Feng, Xiaocheng
    Ma, Sicheng
    Wu, Jiaming
    Gong, Heng
    Qin, Bing
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), 2022, : 3449 - 3467
  • [33] A boosting Self-Training Framework based on Instance Generation with Natural Neighbors for K Nearest Neighbor
    Li, Junnan
    Zhu, Qingsheng
    APPLIED INTELLIGENCE, 2020, 50 (11) : 3535 - 3553
  • [34] A boosting Self-Training Framework based on Instance Generation with Natural Neighbors for K Nearest Neighbor
    Junnan Li
    Qingsheng Zhu
    Applied Intelligence, 2020, 50 : 3535 - 3553
  • [35] Teachers' self-training system via the Distance Educational Model in the Internet environment
    Seki, K
    Takaoka, R
    Inoue, H
    Okamoto, T
    ADVANCED RESEARCH IN COMPUTERS AND COMMUNICATIONS IN EDUCATION, VOL 1: NEW HUMAN ABILITIES FOR THE NETWORKED SOCIETY, 1999, 55 : 436 - 443
  • [36] AXIAL COMPRESSOR MAP GENERATION LEVERAGING AUTONOMOUS SELF-TRAINING AI
    Burlaka, Maksym
    Moroz, Leonid
    PROCEEDINGS OF ASME TURBO EXPO 2022: TURBOMACHINERY TECHNICAL CONFERENCE AND EXPOSITION, GT2022, VOL 1, 2022,
  • [37] Cost Sensitive Active Learning Based on Self-training
    Wu, Yongcheng
    PROCEEDINGS OF 2014 IEEE INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATICS AND COMPUTING (PIC), 2014, : 42 - 45
  • [38] Badminton Self-Training System Based on Virtual Reality
    Tai, Wei-Shen
    Liu, Kuan-Hsien
    2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 1659 - 1663
  • [39] Few Shot Rationale Generation using Self-Training with Dual Teachers
    Veerubhotla, Aditya Srikanth
    Poddar, Lahari
    Yin, Jun
    Szarvas, Gyorgy
    Eswaran, Sharanya
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, 2023, : 4825 - 4838
  • [40] Improving Object Detection Accuracy with Self-Training Based on Bi-Directional Pseudo Label Recovery
    Sajid, Shoaib
    Aziz, Zafar
    Urmonov, Odilbek
    Kim, Hyungwon
    ELECTRONICS, 2024, 13 (12)