反抗日本
发表于 2025-3-21 17:31:56
书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence影响因子(影响力)<br> http://impactfactor.cn/if/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence影响因子(影响力)学科排名<br> http://impactfactor.cn/ifr/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence网络公开度<br> http://impactfactor.cn/at/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence网络公开度学科排名<br> http://impactfactor.cn/atr/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence被引频次<br> http://impactfactor.cn/tc/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence被引频次学科排名<br> http://impactfactor.cn/tcr/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence年度引用<br> http://impactfactor.cn/ii/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence年度引用学科排名<br> http://impactfactor.cn/iir/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence读者反馈<br> http://impactfactor.cn/5y/?ISSN=BK0543934<br><br> <br><br>书目名称Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence读者反馈学科排名<br> http://impactfactor.cn/5yr/?ISSN=BK0543934<br><br> <br><br>
reflection
发表于 2025-3-21 21:27:04
https://doi.org/10.1007/978-981-16-1964-9artificial intelligence; character recognition; computational linguistics; computer systems; data mining
Overthrow
发表于 2025-3-22 03:01:43
http://reply.papertrans.cn/55/5440/543934/543934_3.png
negligence
发表于 2025-3-22 06:31:09
http://reply.papertrans.cn/55/5440/543934/543934_4.png
鬼魂
发表于 2025-3-22 09:35:16
Chinese Punctuation Prediction with Adaptive Attention and Dependency Treeon prediction outperforms BiLSTM+CRF with a gain of 0.292% and 0.127% on accuracy in two datasets respectively. The second proposal outperforms existing methods with a gap of above 4.5% of accuracy and reaches state-of-the-art performance in two datasets.
painkillers
发表于 2025-3-22 16:10:32
http://reply.papertrans.cn/55/5440/543934/543934_6.png
北极熊
发表于 2025-3-22 18:35:43
Improving Relation Extraction Using Semantic Role and Multi-task Learning a Macro-F1 score of 89.96% on the benchmark dataset, outperforming most of the existing methods. More ablation experiments on two different datasets show that semantic role information and multi-task learning can help improve the relation extraction.
熟练
发表于 2025-3-22 23:16:07
http://reply.papertrans.cn/55/5440/543934/543934_8.png
Osteoporosis
发表于 2025-3-23 02:03:41
http://reply.papertrans.cn/55/5440/543934/543934_9.png
Transfusion
发表于 2025-3-23 07:08:04
IBRE: An Incremental Bootstrapping Approach for Chinese Appointment and Dismissal Relation Extractioposed to get high accuracy. Finally, we augment seeds with corrected tuples and apply incremental learning to continually improve performance with least training cost. We build a dataset called ADNP (Appointment and Dismissal News from People.cn) and compare our approach with baselines. Comparison r