eardrum
发表于 2025-3-28 14:51:15
http://reply.papertrans.cn/67/6619/661806/661806_41.png
Nutrient
发表于 2025-3-28 19:11:20
http://reply.papertrans.cn/67/6619/661806/661806_42.png
Gourmet
发表于 2025-3-29 01:26:22
http://reply.papertrans.cn/67/6619/661806/661806_43.png
aerobic
发表于 2025-3-29 03:20:24
Multi-perspective Feature Fusion for Event-Event Relation Extractionderstand the relation structure of the event chain in a document. Existing methods mainly focused on single-event relations, such as causality, while only utilizing trigger words or semantic span as model inputs, ignoring the impact of event arguments and contextual features on events. Hence, we pro
dapper
发表于 2025-3-29 09:11:25
http://reply.papertrans.cn/67/6619/661806/661806_45.png
Pantry
发表于 2025-3-29 14:35:47
A Relational Classification Network Integrating Multi-scale Semantic Features provide high-quality corpus in fields such as machine translation, structured data generation, knowledge graphs, and semantic question answering. Existing relational classification models include models based on traditional machine learning, models based on deep learning, and models based on attent
Melatonin
发表于 2025-3-29 18:20:57
http://reply.papertrans.cn/67/6619/661806/661806_47.png
摇晃
发表于 2025-3-29 21:46:48
http://reply.papertrans.cn/67/6619/661806/661806_48.png
削减
发表于 2025-3-30 02:28:57
Collective Entity Linking with Joint Subgraphsel correlation of linking decisions between different mentions. In this paper, we propose three ideas: (i) build subgraphs made up of partial mentions instead of those in the entire document to improve computation efficiency, (ii) perform joint disambiguation over context and knowledge base (KB), an
我悲伤
发表于 2025-3-30 06:26:04
Coarse-to-Fine Entity Representations for Document-Level Relation Extractions, usually constructing a document-level graph that captures document-aware interactions, can obtain useful entity representations thus helping tackle document-level RE. These methods either focus more on the entire graph, or pay more attention to a part of the graph, e.g., paths between the target