Text generation has always been limited by the lack of corpus data required for language model (LM) training and the low quality of the generated text. Researchers have proposed some solutions, but these solutions are often complex and will greatly increase the consumption of computing resources. Referring to the current main solutions, this paper proposes a lightweight language model (EDA-BoB) based on text augmentation technology and knowledge understanding mechanism. Experiments show that the EDA-BoB model cannot only expand the scale of the training data set but also ensure the data quality at the cost of consuming little computing resources. Moreover, our model is shown to combine the contextual semantics of sentences to generate rich and accurate texts.
Copyright © 2022 Lei Liu et al.