披肩 发表于 2025-3-28 15:35:22
http://reply.papertrans.cn/67/6619/661803/661803_41.pngProcesses 发表于 2025-3-28 22:13:50
0302-9743 ing and Chinese Computing, NLPCC 2021, held in Qingdao, China, in October 2021..The 66 full papers, 23 poster papers, and 27 workshop papers presented were carefully reviewed and selected from 446 submissions. They are organized in the following areas: Fundamentals of NLP; Machine Translation and Mu民间传说 发表于 2025-3-28 23:06:01
Event Argument Extraction via a Distance-Sensitive Graph Convolutional Networkfurther distinguish the roles of event arguments playing in an event. Experiment results on the ACE 2005 English dataset show that the proposed model achieves superior performance than the peer state-of-the-art methods.占线 发表于 2025-3-29 06:45:16
FABERT: A Feature Aggregation BERT-Based Model for Document Rerankingtperforms baseline methods including a feature projection method which projects existing feature vectors into the orthogonal space of generalized feature vector to eliminate common information of generalized feature vectors.mucous-membrane 发表于 2025-3-29 07:38:18
GeoCQA: A Large-Scale Geography-Domain Chinese Question Answering Dataset from Examinationch 80% and 96% accuracy respectively, which shows that GeoCQA is challenging to the current methods and the performance still has space to improve. We will release GeoCQA and our baselines to bring more data sources to the community and hope that it can help to promote much stronger Chinese QA models in the future (.).消耗 发表于 2025-3-29 13:06:04
http://reply.papertrans.cn/67/6619/661803/661803_46.png束缚 发表于 2025-3-29 19:19:28
http://reply.papertrans.cn/67/6619/661803/661803_47.png预感 发表于 2025-3-29 21:35:27
Variational Autoencoder with Interactive Attention for Affective Text Generationon into variational attention with a dynamic update mechanism. At each timestep, the model leverage both the variational attention and hidden representation to decode and predict the target word and then uses the generated results to update the emotional information in attention. It can keep track o