Paper
23 May 2023 Joint training based on adversarial extraction of auxiliary training dataset
Cong Huang
Author Affiliations +
Proceedings Volume 12645, International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023); 126451E (2023) https://doi.org/10.1117/12.2681080
Event: International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023), 2023, Hangzhou, China
Abstract
Task-driven Language Modeling (TLM) can reduce the amount of calculations by an order of magnitude in NLP tasks but achieve the effect of matching the BERT-like large model. It uses BM25 to retrieve relevant data subset from general datasets and combine them with task dataset for joint training, but the extraction process does not consider semantic information, and IRGAN can further extracts semantic information features in the way of adversarial training, and the combination of them can use semantic information to enhance the relevance between the auxiliary training dataset and the labeled task dataset, and then through linearly decreasing joint training in for low-resource tasks have been improved compared to TLM.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cong Huang "Joint training based on adversarial extraction of auxiliary training dataset", Proc. SPIE 12645, International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023), 126451E (23 May 2023); https://doi.org/10.1117/12.2681080
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Data modeling

Gallium nitride

Feature extraction

Image processing

Machine learning

Semantics

RELATED CONTENT


Back to Top