Cite (Informal): An AMR-based Link Prediction Approach for Document-level Event Argument Extraction (Yang et al., ACL 2023) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: = "An inference time.",Īn AMR-based Link Prediction Approach for Document-level Event Argument Extraction Association for Computational Linguistics. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12876–12889, Toronto, Canada. An AMR-based Link Prediction Approach for Document-level Event Argument Extraction. Naoaki Okazaki Venue: ACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 12876–12889 Language: URL: DOI: 10.18653/v1/2023.acl-long.720 Bibkey: yang-etal-2023-amr Cite (ACL): Yuqing Yang, Qipeng Guo, Xiangkun Hu, Yue Zhang, Xipeng Qiu, and Zheng Zhang. Anthology ID: 2023.acl-long.720 Volume: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Month: July Year: 2023 Address: Toronto, Canada Editors: Anna Rogers, Our extensive experiments on WikiEvents and RAMS show that this simpler approach outperforms the state-of-the-art models by 3.63pt and 2.33pt F1, respectively, and do so with reduced 56% inference time. With TAG, we further propose a novel method using graph neural networks as a link prediction model to find event arguments. Since AMR is a generic structure and does not perfectly suit EAE, we propose a novel graph structure, Tailored AMR Graph (TAG), which compresses less informative subgraphs and edge types, integrates span information, and highlights surrounding events in the same document. Motivated by the fact that all event structures can be inferred from AMR, this work reformulates EAE as a link prediction problem on AMR graphs. However, in these works AMR is used only implicitly, for instance, as additional features or training signals. Abstract Recent works have introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE), since AMR provides a useful interpretation of complex semantic structures and helps to capture long-distance dependency.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |