… Softmax function is applied to semantic classification. MSH corpus is adopted to optimize
this model and test its disambiguation performance. Experimental results show that the …

: 深入分析了跨媒体智能关联分析与语义理解理论技术的最新研究进展, 包括多模态数据的统一
表达, 知识引导的数据融合, 跨媒体关联分析, 基于知识图谱的跨媒体表征技术以及面向多模态的…

… A Category hybrid embedding based approach for power text hierarchical classification [J]. …
Text classification model of power equipment defects based on multi-head attention RCNN […

… divided into three categories: embedding-based methods, path-… Representation learning for
question classification via topic … Knowledge graph embedding based question answering[C]//…

: 为了解决论文推荐领域中的数据稀疏性问题, 研究人员通常会引入论文的辅助信息进行改进.
然而, 目前的研究大多集中于辅助信息的语义关联性, 没有考虑到不同辅助信息对论文的重要性也…

… model in news data sets is comparable to the current mainstream neural network recommendation
methods, and its ranking … Embedding-based news recommendation for millions of …

… (DNR) are classified, analyzed and summarized. In the research of NR, modeling users or
… Embedding-based news recommendation for millions of users[C]//Proceedings of the 23rd …

… Document-level multi-topic sentiment classification of Email data with BiLSTM and data …
frame- semantic embedding based data augmentation approach to automatic categorization of …