Flu表流动
发表于 2025-3-26 21:09:15
http://reply.papertrans.cn/24/2340/233947/233947_31.png
确定方向
发表于 2025-3-27 04:21:19
Incremental Inductive Dynamic Network Community Detectionel reuse for dynamic representation learning, constructs incremental node sets for updating the model, reduces training overhead, and quickly obtains node representation vectors for new moments of the network, then completing dynamic network community detection. IINDCD runs without reconstruction and with low retraining overhead.
某人
发表于 2025-3-27 05:59:44
Er-EIR: A Chinese Question Matching Model Based on Word-Level and Sentence-Level Interaction Feature incorporate a co-attention mechanism to capture the interaction information between sentence pairs. By comparing our model with several baseline models on a self-built dataset of university financial question pairs, we have achieved remarkable performance.
collagen
发表于 2025-3-27 12:17:10
http://reply.papertrans.cn/24/2340/233947/233947_34.png
MULTI
发表于 2025-3-27 15:01:23
Prompt-Based and Two-Stage Training for Few-Shot Text Classificationecently, prompt-based learning has emerged as a powerful approach to handling a wide variety of tasks in NLP. It effectively bridges the gap between pre-trained language models (PLMs) and downstream tasks. Verbalizers are key components in prompt-based tuning. Existing manual prompts heavily rely on
伪书
发表于 2025-3-27 21:19:16
A Fine-Grained Image Description Generation Method Based on Joint Objectivest provide coherent and comprehensive textual details about the image content. Currently, most of these methods face two main challenges: description repetition and omission. Moreover, the existing evaluation metrics cannot clearly reflect the performance of models on these two issues. To address the
枕垫
发表于 2025-3-27 21:56:37
Analyzing Collective Intelligence Through Sentiment Networks in Self-organized Douban Communitiesn network communication research. In this study, we present an approach integrating the BERTopic topic model, advanced Natural Language Processing (NLP) techniques, and Social Network Analysis, to meticulously dissect the intricate dynamics of emotion propagation and evolution within collective beha
干涉
发表于 2025-3-28 05:26:42
http://reply.papertrans.cn/24/2340/233947/233947_38.png
CULP
发表于 2025-3-28 07:39:25
Scholar Influence Maximization via Opinion Leader and Graph Embedding Regression in Social Networksence maximization problem. Most Existing influence maximization algorithms relying on scenario-specific centrality measures often underperform when applied to diverse social networks. Many influence maximization deep learning based algorithms use topological embedding to learn the global influence i