Li Jian

Task-Agnostic and Adaptive-Size BERT Compression

2021

While pre-trained language models such as BERT and RoBERTa have achieved impressive results on various natural language processing tasks, they have huge numbers of parameters and suffer from huge computational and memory costs, which make …

Obstacles to Digital Transformation of Labor Education in Chinese Universities, Logical Rationale and Implementation Strategies

2023 · International journal of social science and research

The new development stage of labor education in Chinese colleges and universities focuses on "transformation", and the external obstacles arising from it cannot be ignored. First, the traditional form of labor education in Chinese colleges …