A Graph-Aware Transformer Model for Event Extraction in Hotline Texts

Hotline text data, characterized by their colloquial, fragmented, and noisy nature, present significant challenges for traditional event extraction methods based on formal written text. To address these challenges, this study proposes EENE, a Graph-Aware Transformer model that reformulates multi-stage hotline event extraction as a graph- structured decoding task centered on trigger words to achieve efficient event extraction from fragmented and noisy hotline texts. By integrating BERT-based semantic encoding with Transformer-based dependency modeling, EENE effectively captures long-range contextual dependencies and fine-grained semantic associations for accurately extracting token–token association from fragmented and noisy texts. Furthermore, these connections are utilized to construct a token–token association matrix in which triggers serve as central nodes and arguments as edge nodes, thereby enabling event extraction by structured graph reasoning. Multi-stage event extraction is thus transformed into a single-step association extraction task, effectively avoiding cascading errors and improving the accuracy of event extraction. Experimental results on two self-built Chinese hotline datasets covering urban flooding, public complaints, and help requests demonstrate that EENE achieves state-of-the-art performance, surpassing representative baselines such as EDEE and CASEE by 5.15% and 15.44% in average F1-score, respectively. These findings confirm that graph-structured event modeling can robustly extract complete event information from noisy, colloquial hotline text, supporting applications in urban governance, emergency response, and public service monitoring.