The main task of discourse element identification is to identify discourse element units and classify them. Aiming at the lack of understanding of context dependence in discourse element identification, this study proposes a discourse element identification model based on BiLSTM-Attention to improve the accuracy of discourse element identification in argumentative essays. The model uses sentence structure and positional encoding to identify sentence component relationships and further acquires deep context-related information through bidirectional long short-term memory (BiLSTM). Attention mechanism is introduced to optimize the model feature vectors and improve the accuracy of text classification. Finally, inter-sentence multi-head self-attention is used to obtain the relationships between the content and structure of sentences, so as to make up for the distant sentence dependence. Compared with baseline models such as HBiLSTM and BERT, the accuracy on Chinese and English datasets is improved by 1.3% and 3.6% respectively under the same parameters and the same environmental conditions, which verifies the effectiveness of the model in the discourse element identification task.