Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Utilizing Contextual Clues and Role Correlations for Enhancing Document-level Event Argument Extraction (2310.05116v4)

Published 8 Oct 2023 in cs.CL and cs.IR

Abstract: Document-level event argument extraction is a crucial yet challenging task within the field of information extraction. Current mainstream approaches primarily focus on the information interaction between event triggers and their arguments, facing two limitations: insufficient context interaction and the ignorance of event correlations. Here, we introduce a novel framework named CARLG (Contextual Aggregation of clues and Role-based Latent Guidance), comprising two innovative components: the Contextual Clues Aggregation (CCA) and the Role-based Latent Information Guidance (RLIG). The CCA module leverages the attention weights derived from a pre-trained encoder to adaptively assimilates broader contextual information, while the RLIG module aims to capture the semantic correlations among event roles. We then instantiate the CARLG framework into two variants based on two types of current mainstream EAE approaches. Notably, our CARLG framework introduces less than 1% new parameters yet significantly improving the performance. Comprehensive experiments across the RAMS, WikiEvents, and MLEE datasets confirm the superiority of CARLG, showing significant superiority in terms of both performance and inference speed compared to major benchmarks. Further analyses demonstrate the effectiveness of the proposed modules.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (89)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, .
  2. Text summarization techniques: a brief survey. arXiv preprint arXiv:1707.02268, .
  3. Large scale spectral clustering via landmark-based sparse representation. IEEE Transactions on Cybernetics, 45, 1669–1680.
  4. End-to-end object detection with transformers. In European conference on computer vision (pp. 213–229). Springer.
  5. Relation extraction with contextualized relation embedding (CRE). In Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures. Online: Association for Computational Linguistics.
  6. Event extraction via dynamic multi-pooling convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Beijing, China: Association for Computational Linguistics.
  7. BERT: Pre-training of deep bidirectional transformers for language understanding. In 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, Minnesota: Association for Computational Linguistics.
  8. Community evolution prediction based on a self-adaptive timeframe in social networks. Knowledge-Based Systems, 275, 110687. URL: https://www.sciencedirect.com/science/article/pii/S0950705123004379. doi:https://doi.org/10.1016/j.knosys.2023.110687.
  9. A survey for trust-aware recommender systems: A deep learning perspective. Knowledge-Based Systems, 249, 108954. URL: https://www.sciencedirect.com/science/article/pii/S0950705122004622. doi:https://doi.org/10.1016/j.knosys.2022.108954.
  10. Document-level event role filler extraction using multi-granularity contextualized encoding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online: Association for Computational Linguistics.
  11. Event extraction by answering (almost) natural questions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online: Association for Computational Linguistics.
  12. GRIT: Generative role-filler transformers for document-level event entity extraction. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Online: Association for Computational Linguistics.
  13. Multi-sentence argument linking. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 8057–8077).
  14. Document-level relation extraction with relation correlations. arXiv:2212.10171.
  15. Revisiting event argument extraction: Can eae models learn better when being aware of event co-occurrences? arXiv preprint arXiv:2306.00502, .
  16. Ampere: Amr-aware prefix for generation-based event argument extraction model. arXiv preprint arXiv:2305.16734, .
  17. Role knowledge prompting for document-level event argument extraction. Applied Sciences, 13, 3041.
  18. Visual–textual hybrid sequence matching for joint reasoning. IEEE Transactions on Cybernetics, 51, 5692--5705.
  19. Sman: Stacked multimodal attention network for cross-modal image–text retrieval. IEEE Transactions on Cybernetics, 52, 1086--1097. doi:10.1109/TCYB.2020.2985716.
  20. Hard negative sampling via regularized optimal transport for contrastive representation learning. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1--8). IEEE.
  21. Supervised contrastive learning with hard negative samples. arXiv preprint arXiv:2209.00078, .
  22. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
  23. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461, .
  24. Semi-automatic data enhancement for document-level relation extraction with distant supervision from large language models. arXiv preprint arXiv:2311.07314, .
  25. GAIA: A fine-grained multimedia knowledge extraction system. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Online: Association for Computational Linguistics.
  26. Document-level event argument extraction by conditional generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Online: Association for Computational Linguistics.
  27. Making recommender systems forget: Learning and unlearning for erasable recommendation. Knowledge-Based Systems, 283, 111124. URL: https://www.sciencedirect.com/science/article/pii/S0950705123008742. doi:https://doi.org/10.1016/j.knosys.2023.111124.
  28. Feature manipulation for ddpm based change detection. arXiv preprint arXiv:2403.15943, .
  29. Focal loss for dense object detection. In 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 2999--3007). doi:10.1109/ICCV.2017.324.
  30. Document-level event argument extraction with a chain reasoning paradigm. In A. Rogers, J. Boyd-Graber, & N. Okazaki (Eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 9570--9583). Toronto, Canada: Association for Computational Linguistics. URL: https://aclanthology.org/2023.acl-long.532. doi:10.18653/v1/2023.acl-long.532.
  31. Exploiting argument information to improve event detection via supervised attention mechanisms. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Vancouver, Canada: Association for Computational Linguistics.
  32. Enhancing document-level event argument extraction with contextual clues and role relevance. In Findings of the Association for Computational Linguistics: ACL 2023. Toronto, Canada: Association for Computational Linguistics.
  33. Document-level relation extraction with structure enhanced transformer encoder. In Proc. of IJCNN.
  34. Dynamic prefix-tuning for generative template-based event extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin, Ireland: Association for Computational Linguistics.
  35. Jointly multiple events extraction via attention-based graph information aggregation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium: Association for Computational Linguistics.
  36. Roberta: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692.
  37. Alsa: Adversarial learning of supervised attentions for visual question answering. IEEE Transactions on Cybernetics, 52, 4520--4533. doi:10.1109/TCYB.2020.3029423.
  38. Explainable document-level event extraction via back-tracing to sentence-level event clues. Knowledge-Based Systems, 248, 108715.
  39. Weak disambiguation for partial structured output learning. IEEE Transactions on Cybernetics, 52, 1258--1268. doi:10.1109/TCYB.2020.3000053.
  40. Trigger is non-central: Jointly event extraction via label-aware representations with multi-task learning. Knowledge-Based Systems, 252, 109480.
  41. Prompt for extraction? paie: Prompting argument interaction for event argument extraction. arXiv preprint arXiv:2202.12109, .
  42. Prompt for extraction? PAIE: Prompting argument interaction for event argument extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin, Ireland: Association for Computational Linguistics.
  43. Visualizing data using t-sne. Journal of Machine Learning Research, 9, 2579--2605.
  44. Mitchell, J. C. (1974). Social networks. Annual review of anthropology, 3, 279--299.
  45. Contextualized soft prompts for extraction of event arguments. In Findings of the Association for Computational Linguistics: ACL 2023 (pp. 4352--4361).
  46. Event detection and domain adaptation with convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Beijing, China: Association for Computational Linguistics.
  47. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730--27744.
  48. Deep contextualized word representations. arXiv preprint arXiv:1802.05365, .
  49. Document-level event argument extraction via optimal transport. In Findings of the Association for Computational Linguistics: ACL 2022. Dublin, Ireland: Association for Computational Linguistics.
  50. Event extraction across multiple levels of biological organization. Bioinformatics, 28, i575--i581. doi:10.1093/bioinformatics/bts407.
  51. CLIO: Role-interactive multi-event head attention network for document-level event extraction. In Proceedings of the 29th International Conference on Computational Linguistics. Gyeongju, Republic of Korea: International Committee on Computational Linguistics.
  52. Retrieve-and-sample: Document-level event argument extraction via hybrid retrieval augmentation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 293--306).
  53. Riemannian adaptive optimization algorithm and its application to natural language processing. IEEE Transactions on Cybernetics, 52, 7328--7339. doi:10.1109/TCYB.2021.3049845.
  54. Extensive evaluation of transformer-based architectures for adverse drug events extraction. Knowledge-Based Systems, 275, 110675. URL: https://www.sciencedirect.com/science/article/pii/S0950705123004252. doi:https://doi.org/10.1016/j.knosys.2023.110675.
  55. A tree-like structured perceptron for transition-based biomedical event extraction. Knowledge-Based Systems, 283, 111180. URL: https://www.sciencedirect.com/science/article/pii/S0950705123009309. doi:https://doi.org/10.1016/j.knosys.2023.111180.
  56. Discriminative exemplar coding for sign language recognition with kinect. IEEE Transactions on Cybernetics, 43, 1418--1428. doi:10.1109/TCYB.2013.2265337.
  57. Prescribed performance control of constrained euler–language systems chasing unknown targets. IEEE Transactions on Cybernetics, 53, 4829--4840. doi:10.1109/TCYB.2021.3134819.
  58. Improving event detection via open-domain trigger knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online: Association for Computational Linguistics.
  59. DeepEventMine: end-to-end neural nested event extraction from biomedical texts. Bioinformatics, 36, 4910--4917.
  60. Tucker, L. R. et al. (1964). The extension of factor analysis to three-dimensional matrices. Contributions to mathematical psychology, 110119.
  61. Attention is all you need. Advances in neural information processing systems, 30.
  62. Entity, relation, and event extraction with contextualized span representations. In 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: Association for Computational Linguistics.
  63. Query and extract: Refining event extraction as type-oriented binary decoding. In Findings of the Association for Computational Linguistics: ACL 2022. Dublin, Ireland: Association for Computational Linguistics.
  64. CLEVE: Contrastive Pre-training for Event Extraction. In 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: Association for Computational Linguistics.
  65. Trigger is not sufficient: Exploiting frame-aware knowledge for implicit event argument extraction. In 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: Association for Computational Linguistics.
  66. Two-level lstm for sentiment analysis with lexicon embedding and polar flipping. IEEE Transactions on Cybernetics, 52, 3867--3879.
  67. EmRel: Joint representation of entities and embedded relations for multi-triple extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Seattle, United States: Association for Computational Linguistics.
  68. Large language models for generative information extraction: A survey. arXiv preprint arXiv:2312.17617, .
  69. Multi-view entity type overdependency reduction for event argument extraction. Knowledge-Based Systems, 265, 110375.
  70. Multi-view entity type overdependency reduction for event argument extraction. Knowledge-Based Systems, 265, 110375. URL: https://www.sciencedirect.com/science/article/pii/S0950705123001259. doi:https://doi.org/10.1016/j.knosys.2023.110375.
  71. Document-level event extraction via heterogeneous graph-based interaction model with a tracker. In 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: Association for Computational Linguistics.
  72. A two-stream amr-enhanced model for document-level event argument extraction. arXiv e-prints, (pp. arXiv--2205).
  73. Discriminative reasoning for document-level relation extraction. arXiv:2106.01562.
  74. Event detection with multi-order graph convolution and aggregated attention. In 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: Association for Computational Linguistics.
  75. Document-level event extraction via parallel prediction networks. In 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: Association for Computational Linguistics.
  76. Anchor link prediction across social networks based on multiple consistency. Knowledge-Based Systems, 257, 109939. URL: https://www.sciencedirect.com/science/article/pii/S0950705122010322. doi:https://doi.org/10.1016/j.knosys.2022.109939.
  77. EA2E: Improving consistency with event awareness for document-level argument extraction. In Findings of the Association for Computational Linguistics: NAACL 2022. Seattle, United States: Association for Computational Linguistics.
  78. Nc-dre: Leveraging non-entity clue information for document-level relation extraction. arXiv preprint arXiv:2204.00255, .
  79. Document-level relation extraction as semantic segmentation. In IJCAI.
  80. Diagnostic prediction with sequence-of-sets representation learning for clinical events, .
  81. Ultra: Unleash llms’ potential for event argument extraction through hierarchical modeling and pair-wise refinement. arXiv preprint arXiv:2401.13218, .
  82. Effect of confidence and explanation on accuracy and trust calibration in ai-assisted decision making. In Proceedings of the 2020 conference on fairness, accountability, and transparency (pp. 295--305).
  83. Contextualized word representations for reading comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 5412--5421).
  84. A two-step approach for implicit event argument detection. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 7479--7485).
  85. Mutually improved response generation and dialogue summarization for multi-domain task-oriented dialogue systems. Knowledge-Based Systems, 279, 110927. URL: https://www.sciencedirect.com/science/article/pii/S0950705123006779. doi:https://doi.org/10.1016/j.knosys.2023.110927.
  86. Doc2EDAG: An end-to-end document-level framework for Chinese financial event extraction. In 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: Association for Computational Linguistics.
  87. Heuristics-driven link-of-analogy prompting: Enhancing large language models for document-level event argument extraction. arXiv preprint arXiv:2311.06555, .
  88. Eace: A document-level event argument extraction model with argument constraint enhancement. Information Processing & Management, 61, 103559.
  89. Document-level relation extraction with adaptive thresholding and localized context pooling. In Proceedings of the AAAI conference on artificial intelligence (pp. 14612--14620). volume 35.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Wanlong Liu (13 papers)
  2. Dingyi Zeng (8 papers)
  3. Li Zhou (216 papers)
  4. Yichen Xiao (10 papers)
  5. Weishan Kong (1 paper)
  6. Malu Zhang (43 papers)
  7. Shaohuan Cheng (6 papers)
  8. Hongyang Zhao (5 papers)
  9. Wenyu Chen (49 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now