Abstract: Event extraction (EE) is a complex natural language processing (NLP) task that aims at identifying and classifying triggers and arguments in raw text. The polysemy of triggers and arguments stands out as one of the key challenges affecting the precise extraction of events. The existing approaches commonly consider the semantics distribution of triggers and arguments to be balanced. However, the sample quantities of the different semantics in the same trigger or argument vary in real-world scenarios, leading to a biased semantic distribution. The bias introduces two challenges: (1) low-frequency semantics are difficult to identify and (2) high-frequency semantics are often mistakenly identified. To tackle these challenges, we propose an adaptive learning method with the reward–penalty mechanism for balancing the semantic distribution in polysemous triggers and arguments. The reward–penalty mechanism balances the semantic distribution by enlarging the gap between the target and nontarget semantics by rewarding correct classifications and penalizing incorrect classifications. Additionally, we propose the sentence-level event situation awareness (SA) mechanism to guide the encoder to accurately learn the knowledge of events mentioned in the sentence, thereby enhancing target event semantics in the distribution of polysemous triggers and arguments. Finally, for various semantics in different tasks, we propose task-specific semantics decoders to precisely identify the boundaries of the predicted triggers and arguments for the semantics. Our experimental results on ACE2005 and its variants, along with ERE benchmarks, demonstrate the superiority of our approach over single-task and multi-task EE baselines.