Correspondence addresses are widely used in e-commerce logistics, government registration, financial transportation and other fields. The analysis and aggregation of communication addresses is an essential service. However, in practical applications, the address text has the characteristics of free writing, many default aliases, and a strong locality, which cause some difficulties in identifying addresses. To address the above problems, this paper proposes a DCF model (Dropout and Constrained Features) combined with an entity extractor (referred to as ENEX) using a baseline BERT model, to perform named entity recognition on Chinese address element data. In this paper, we use hierarchical learning rate setting and learning rate decay strategies to improve the accuracy of recognition and adversarial training to improve the robustness of the model. Compared with the BERT-CRF model, the F1 value of our model is enhanced by 4.15% in the Chinese address element parsing dataset, and its F1 value can reach 93.34%. This proves the effectiveness of the ENEX-DCF model in Chinese address element recognition.

In e-commerce logistics, government registration, financial transportation and other fields, communication addresses are required. Analyzing the communication address is crucial. There are various challenges in address recognition due to the address text’s features of free writing, numerous aliases and significant text similarity. This study shows an ENEX-FP address recognition model, which consists of an entity extractor (ENEX) and a feature processor (FP) for address recognition, as a solution to the issues mentioned. This study uses adversarial training to enhance the model’s robustness and a hierarchical learning rate setup and learning rate attenuation technique to enhance recognition accuracy. Compared with traditional named entity recognition models, our model achieves an F1-score of 93.47% and 94.59% in the dataset, demonstrating the ENEX-FP model’s effectiveness in recognizing addresses.