Modeling Semantic-Aware Prompt-Based Argument Extractor in Documents
Source abstract
Abstract
Event extraction aims to identify and structure event information from unstructured text, playing a critical role in real-world applications such as news analysis, public opinion discovery, and intelligence gathering. Traditional approaches, however, struggle with event co-occurrence and long-distance dependencies. To address these challenges, we introduce the Semantic-aware Prompt-based Argument Extractor (SPARE) model, which integrates entity extraction, heterogeneous graph construction, event type detection, and argument filling. By constructing a document–sentence–entity heterogeneous graph and employing graph convolutional networks (GCNs), the model effectively captures global semantic associations and interactions between cross-sentence triggers and arguments. Additionally, a position-aware semantic role (SRL) attention mechanism is proposed to enhance the association between semantic and positional information, improving argument extraction accuracy in the context of event co-occurrence. The experimental outcomes on the Richly Annotated Multilingual Schema-guided Event Structure (RAMS) and WikiEvents datasets display considerable F1 score improvements, which confirms the model’s effectiveness.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Software Engineering Research · Natural Language Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
Funding
National Natural Science Foundation of China · high-level Innovative Teams of Beijing Municipal Institutions · the National Science and Technology Major Project · the Beijing Municipal 530 Social Science Foundation Annual Planning Project · Beijing Scholars Program
References (53)
Show source-provided references
1. A Survey of Event Extraction From Text10.1109/ACCESS.2019.2956831 ↗
2. Saxena, A. (2023, January 15–16). A Survey of Session-Based Recommender Systems. Proceedings of the 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), Greater Noida, India.10.1109/ICAC3N60023.2023.10541576 ↗
3. Improved GPT2 Event Extraction Method Based on Mixed Attention Collaborative Layer Vector10.1109/ACCESS.2024.3487836 ↗
4. Zheng, S., Cao, W., Xu, W., and Bian, J. (2019, January 3–7). Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extraction. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.10.18653/v1/D19-1032 ↗
5. Zhou, Y., Chen, Y., Zhao, J., Wu, Y., Xu, J., and Li, J. (2021, January 2–9). What the Role is vs. What Plays the Role: Semi-Supervised Event Argument Extraction via Dual Question Answering. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI, Virtual Event.
6. Improving question answering for event-focused questions in temporal collections of news articles10.1007/s10791-020-09387-9 ↗
7. Hong, Z., and Liu, J. (2024, January 11–16). Towards Better Question Generation in QA-based Event Extraction. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand.10.18653/v1/2024.findings-acl.535 ↗
8. Zero-Shot Video Event Detection With High-Order Semantic Concept Discovery and Matching10.1109/TMM.2021.3073624 ↗
9. Joint Argument Inference in Chinese Event Extraction with Argument Consistency and Event Relevance10.1109/TASLP.2015.2497148 ↗
10. You, T., Li, Z., Fan, Z., Yin, C., He, Y., Cai, J., Fu, J., and Wei, Z. (2024, January 1–3). An Iterative Framework for Document-Level Event Argument Extraction Assisted by Long Short-Term Memory. Proceedings of the Natural Language Processing and Chinese Computing, Hangzhou, China.10.1007/978-981-97-9434-8_6 ↗
11. FineCSDA: Boosting Document-Level Event Argument Extraction with Fine-Grained Data Augmentation
12. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2–7). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA.
13. Radford, A., and Narasimhan, K. (2025, March 08). Improving Language Understanding by Generative Pre-Training. Available online: https://api.semanticscholar.org/CorpusID:49313245.
14. Language Models are Few-Shot Learners
15. Vlachos, A., and Augenstein, I. (2023, January 2–4). A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia.
16. Wan, Q., Wan, C., Xiao, K., Liu, D., Li, C., Zheng, B., Liu, X., and Hu, R. (2023, January 9–14). Joint Document-Level Event Extraction via Token-Token Bidirectional Event Completed Graph. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.10.18653/v1/2023.acl-long.584 ↗
17. Gao, J., Zhao, H., Yu, C., and Xu, R. (2023). Exploring the Feasibility of ChatGPT for Event Extraction. arXiv.
18. Wei, X., Cui, X., Cheng, N., Wang, X., Zhang, X., Huang, S., Xie, P., Xu, J., Chen, Y., and Zhang, M. (2023). Zero-Shot Information Extraction Via Chatting with ChatGPT. arXiv.
19. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Red Hook, NY, USA.
20. Beltagy, I., Peters, M.E., and Cohan, A. (2004). Longformer: The Long-Document Transformer. arXiv.
21. Zaheer, M., Guruganesh, G., Dubey, A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., and Yang, L. (2020, January 6–12). Big bird: Transformers for longer sequences. Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS ’20), Red Hook, NY, USA.
22. Exploring the limits of transfer learning with a unified text-to-text transformer
23. PaLM: Scaling Language Modeling with Pathways
24. Huang, L., Cassidy, T., Feng, X., Ji, H., Voss, C.R., Han, J., and Sil, A. (2016, January 7–12). Liberal Event Extraction and Event Schema Induction. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany.10.18653/v1/P16-1025 ↗
25. Chambers, N. (2013, January 18–21). Event Schema Induction with a Probabilistic Entity-Driven Model. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, DC, USA.10.18653/v1/D13-1185 ↗
26. Cheung, J.C.K., Poon, H., and Vanderwende, L. (2013, January 9–14). Probabilistic Frame Induction. Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, GA, USA.
27. Shen, J., Zhang, Y., Ji, H., and Han, J. (2021, January 7–11). Corpus-based Open-Domain Event Type Induction. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic.10.18653/v1/2021.emnlp-main.441 ↗
28. Huang, L., and Ji, H. (2020, January 16–20). Semi-supervised New Event Type Induction and Event Detection. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.10.18653/v1/2020.emnlp-main.53 ↗
29. Li, S., Ji, H., and Han, J. (2022, January 7–11). Open Relation and Event Type Discovery with Type Abstraction. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates.10.18653/v1/2022.emnlp-main.461 ↗
30. Tang, J., Lin, H., Li, Z., Lu, Y., Han, X., and Sun, L. (2023). Harvesting Event Schemas from Large Language Models. arXiv.10.1007/978-981-99-7224-1_5 ↗
31. Xu, R., Wang, P., Liu, T., Zeng, S., Chang, B., and Sui, Z. (2022, January 10–15). A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, DC, USA.10.18653/v1/2022.naacl-main.370 ↗
32. Liu, W., Cheng, S., Zeng, D., and Hong, Q. (2023, January 9–14). Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, Toronto, ON, Canada.10.18653/v1/2023.findings-acl.817 ↗
33. Tan, L., Hu, Y., Cao, J., and Tan, Z. (2024). AssocKD: An Association-Aware Knowledge Distillation Method for Document-Level Event Argument Extraction. Mathematics, 12.10.3390/math12182901 ↗
34. Ma, Y., Wang, Z., Cao, Y., Li, M., Chen, M., Wang, K., and Shao, J. (2022, January 22–27). Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.10.18653/v1/2022.acl-long.466 ↗
35. Nguyen, C., Man, H., and Nguyen, T. (2023, January 9–14). Contextualized Soft Prompts for Extraction of Event Arguments. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, Toronto, ON, Canada.10.18653/v1/2023.findings-acl.266 ↗
36. Li, H., Cao, Y., Ren, Y., Fang, F., Zhang, L., Li, Y., and Wang, S. (2023, January 6–10). Intra-Event and Inter-Event Dependency-Aware Graph Network for Event Argument Extraction. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.10.18653/v1/2023.findings-emnlp.421 ↗
37. Zhang, M., and Chen, H. (2024). Document-Level Event Argument Extraction with Sparse Representation Attention. Mathematics, 12.10.3390/math12172636 ↗
38. Zhang, G., Zhang, H., Wang, Y., Li, R., Tan, H., and Liang, J. (2024, January 11–16). Hyperspherical Multi-Prototype with Optimal Transport for Event Argument Extraction. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand.10.18653/v1/2024.acl-long.502 ↗
39. Wei, K., Sun, X., Zhang, Z., Zhang, J., Zhi, G., and Jin, L. (2021, January 1–6). Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online.10.18653/v1/2021.acl-long.360 ↗
40. Du, X., Li, S., and Ji, H. (2022, January 22–27). Dynamic Global Memory for Document-level Argument Extraction. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.10.18653/v1/2022.acl-long.361 ↗
41. Ren, Y., Cao, Y., Guo, P., Fang, F., Ma, W., and Lin, Z. (2023, January 9–14). Retrieve-and-Sample: Document-level Event Argument Extraction via Hybrid Retrieval Augmentation. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.10.18653/v1/2023.acl-long.17 ↗
42. Wang, X., Jia, S., Han, X., Liu, Z., Li, J., Li, P., and Zhou, J. (2020, January 4–7). Neural Gibbs Sampling for Joint Event Argument Extraction. Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, Suzhou, China.10.18653/v1/2020.aacl-main.21 ↗
43. Sheng, J., Guo, S., Yu, B., Li, Q., Hei, Y., Wang, L., Liu, T., and Xu, H. (2021, January 1–6). CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction. Proceedings of the Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, Online.10.18653/v1/2021.findings-acl.14 ↗
44. Xu, R., Liu, T., Li, L., and Chang, B. (2021, January 1–6). Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online.10.18653/v1/2021.acl-long.274 ↗
45. Token-Event-Role Structure-Based Multi-Channel Document-Level Event Extraction
46. The viterbi algorithm10.1109/PROC.1973.9030 ↗
47. Ebner, S., Xia, P., Culkin, R., Rawlins, K., and Van Durme, B. (2020, January 5–10). Multi-Sentence Argument Linking. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.718 ↗
48. Li, S., Ji, H., and Han, J. (2021, January 6–11). Document-Level Event Argument Extraction by Conditional Generation. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online.10.18653/v1/2021.naacl-main.69 ↗
49. Loshchilov, I., and Hutter, F. (2017, January 24–26). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations, Toulon, France.
50. Yang, Y., Guo, Q., Hu, X., Zhang, Y., Qiu, X., and Zhang, Z. (2023, January 9–14). An AMR-based Link Prediction Approach for Document-level Event Argument Extraction. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.10.18653/v1/2023.acl-long.720 ↗
51. He, Y., Hu, J., and Tang, B. (2023, January 9–14). Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.10.18653/v1/2023.acl-long.701 ↗
52. Shuang, K., Zhouji, Z., Wang,, Q., and Guo, J. (2024, January 11–16). Energizing LLMs’ Emergence Capabilities for Document-Level Event Argument Extraction. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand.10.18653/v1/2024.findings-acl.328 ↗
53. Liu, W., Zhou, L., Zeng, D., Xiao, Y., Cheng, S., Zhang, C., Lee, G., Zhang, M., and Chen, W. (2024, January 11–16). Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand.10.18653/v1/2024.findings-acl.564 ↗