Recouple Event Field via Probabilistic Bias for Event Extraction
This work addresses event extraction for natural language processing applications, but it is incremental as it builds on existing PLM-based methods with a focus on field information.
The authors tackled the problem of event extraction by addressing the neglect of trigger/argument field information in pre-trained language models, proposing a probabilistic recoupling framework that improved performance on standard datasets.
Event Extraction (EE), aiming to identify and classify event triggers and arguments from event mentions, has benefited from pre-trained language models (PLMs). However, existing PLM-based methods ignore the information of trigger/argument fields, which is crucial for understanding event schemas. To this end, we propose a Probabilistic reCoupling model enhanced Event extraction framework (ProCE). Specifically, we first model the syntactic-related event fields as probabilistic biases, to clarify the event fields from ambiguous entanglement. Furthermore, considering multiple occurrences of the same triggers/arguments in EE, we explore probabilistic interaction strategies among multiple fields of the same triggers/arguments, to recouple the corresponding clarified distributions and capture more latent information fields. Experiments on EE datasets demonstrate the effectiveness and generalization of our proposed approach.