A Comprehensive Comparison of Pre-training Language Models (2106.11483v9)

Abstract: Recently, the development of pre-trained LLMs has brought NLP tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained LLMs. We pre-train a list of transformer-based models with the same amount of text and the same training steps. The experimental results shows that the most improvement upon the origin BERT is adding the RNN-layer to capture more contextual information for short text understanding. But the conclusion is: There are no remarkable improvement for short text understanding for similar BERT structures. Data-centric method[12] can achieve better performance.