Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap between the retriever and the inference model. These issues limit the diversity and quality of the retrieved information. In this paper, we propose a Compressive Memory-based Retrieval (CMR) mechanism for EAE, which addresses the two limitations mentioned above. Our compressive memory, designed as a dynamic matrix that effectively caches retrieved information and supports continuous updates, overcomes the limitations of input length. Additionally, after pre-loading all candidate demonstrations into the compressive memory, the model further retrieves and filters relevant information from the memory based on the input query, bridging the gap between the retriever and the inference model. Extensive experiments show that our method achieves new state-of-the-art performance on three public datasets (RAMS, WikiEvents, ACE05), significantly outperforming existing retrieval-based EAE methods.
Wanlong Liu, Enqi Zhang, Shaohuan Cheng, Dingyi Zeng, Li Zhou, Chen Zhang, Malu Zhang, and Wenyu Chen. 2025.A Compressive Memory-based Retrieval Approach for Event Argument Extraction. InProceedings of the 31st International Conference on Computational Linguistics, pages 1278–1293, Abu Dhabi, UAE. Association for Computational Linguistics.
@inproceedings{liu-etal-2025-compressive, title = "A Compressive Memory-based Retrieval Approach for Event Argument Extraction", author = "Liu, Wanlong and Zhang, Enqi and Cheng, Shaohuan and Zeng, Dingyi and Zhou, Li and Zhang, Chen and Zhang, Malu and Chen, Wenyu", editor = "Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven", booktitle = "Proceedings of the 31st International Conference on Computational Linguistics", month = jan, year = "2025", address = "Abu Dhabi, UAE", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2025.coling-main.85/", pages = "1278--1293", abstract = "Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap between the retriever and the inference model. These issues limit the diversity and quality of the retrieved information. In this paper, we propose a Compressive Memory-based Retrieval (CMR) mechanism for EAE, which addresses the two limitations mentioned above. Our compressive memory, designed as a dynamic matrix that effectively caches retrieved information and supports continuous updates, overcomes the limitations of input length. Additionally, after pre-loading all candidate demonstrations into the compressive memory, the model further retrieves and filters relevant information from the memory based on the input query, bridging the gap between the retriever and the inference model. Extensive experiments show that our method achieves new state-of-the-art performance on three public datasets (RAMS, WikiEvents, ACE05), significantly outperforming existing retrieval-based EAE methods."}
%0 Conference Proceedings%T A Compressive Memory-based Retrieval Approach for Event Argument Extraction%A Liu, Wanlong%A Zhang, Enqi%A Cheng, Shaohuan%A Zeng, Dingyi%A Zhou, Li%A Zhang, Chen%A Zhang, Malu%A Chen, Wenyu%Y Rambow, Owen%Y Wanner, Leo%Y Apidianaki, Marianna%Y Al-Khalifa, Hend%Y Eugenio, Barbara Di%Y Schockaert, Steven%S Proceedings of the 31st International Conference on Computational Linguistics%D 2025%8 January%I Association for Computational Linguistics%C Abu Dhabi, UAE%F liu-etal-2025-compressive%X Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap between the retriever and the inference model. These issues limit the diversity and quality of the retrieved information. In this paper, we propose a Compressive Memory-based Retrieval (CMR) mechanism for EAE, which addresses the two limitations mentioned above. Our compressive memory, designed as a dynamic matrix that effectively caches retrieved information and supports continuous updates, overcomes the limitations of input length. Additionally, after pre-loading all candidate demonstrations into the compressive memory, the model further retrieves and filters relevant information from the memory based on the input query, bridging the gap between the retriever and the inference model. Extensive experiments show that our method achieves new state-of-the-art performance on three public datasets (RAMS, WikiEvents, ACE05), significantly outperforming existing retrieval-based EAE methods.%U https://aclanthology.org/2025.coling-main.85/%P 1278-1293
Wanlong Liu, Enqi Zhang, Shaohuan Cheng, Dingyi Zeng, Li Zhou, Chen Zhang, Malu Zhang, and Wenyu Chen. 2025.A Compressive Memory-based Retrieval Approach for Event Argument Extraction. InProceedings of the 31st International Conference on Computational Linguistics, pages 1278–1293, Abu Dhabi, UAE. Association for Computational Linguistics.