分类： 计算机科学 >> 自然语言理解与机器翻译 提交时间： 2022-03-04
摘要： The rise and application of neural network has successfully promoted the research of pattern recognition and data mining.In recent years, graph neural network has attracted more and more attention. It has some applications in text classification, sequence annotation, neural machine translation, relation extraction, image classification and other fields. This review mainly integrates the existing research on semi-supervised or unsupervised graph neural network. The research work of this paper is mainly classified in three aspects, one is based on the classification of research questions, the other is based on the classification of research methods, and the third is based on the classification of measures.The main research problems are the low-dimensional representation of nodes in graphs and the over-smooth problem in the process of message transfer. The research methods mainly focus on the graph embedding algorithm, such as the graph embedding algorithm based on probability graph and the method based on deep learning. The measurement methods mainly focus on the accuracy and efficiency of the algorithm and model.Finally, this paper also puts forward the feasible future research direction, which provides reference for readers.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-27 合作期刊: 《数据智能（英文）》
摘要： The Chinese Software Developer Network (CSDN) is one of the largest information technology communities and service platforms in China. This paper describes the user profiling for CSDN, an evaluation track of SMP Cup 2017. It contains three tasks: (1) user document keyphrase extraction, (2) user tagging and (3) user growth value prediction. In the first task, we treat keyphrase extraction as a classification problem and train a Gradient-Boosting-Decision-Tree model with comprehensive features. In the second task, to deal with class imbalance and capture the interdependency between classes, we propose a two-stage framework: (1) for each class, we train a binary classifier to model each class against all of the other classes independently; (2) we feed the output of the trained classifiers into a softmax classifier, tagging each user with multiple labels. In the third task, we propose a comprehensive architecture to predict user growth value. Our contributions in this paper are summarized as follows: (1) we extract various types of features to identify the key factors in user value growth; (2) we use the semi-supervised method and the stacking technique to extend labeled data sets and increase the generality of the trained model, resulting in an impressive performance in our experiments. In the competition, we achieved the first place out of 329 teams.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： COVID-19 evolves rapidly and an enormous number of people worldwide desire instant access to COVID- 19 information such as the overview, clinic knowledge, vaccine, prevention measures, and COVID-19 mutation. Question answering (QA) has become the mainstream interaction way for users to consume the ever-growing information by posing natural language questions. Therefore, it is urgent and necessary to develop a QA system to offer consulting services all the time to relieve the stress of health services. In particular, people increasingly pay more attention to complex multi-hop questions rather than simple ones during the lasting pandemic, but the existing COVID-19 QA systems fail to meet their complex information needs. In this paper, we introduce a novel multi-hop QA system called COKG-QA, which reasons over multiple relations over large-scale COVID-19 Knowledge Graphs to return answers given a question. In the field of question answering over knowledge graph, current methods usually represent entities and schemas based on some knowledge embedding models and represent questions using pre-trained models. While it is convenient to represent different knowledge (i.e., entities and questions) based on specified embeddings, an issue raises that these separate representations come from heterogeneous vector spaces. We align question embeddings with knowledge embeddings in a common semantic space by a simple but effective embedding projection mechanism. Furthermore, we propose combining entity embeddings with their corresponding schema embeddings which served as important prior knowledge, to help search for the correct answer entity of specified types. In addition, we derive a large multi-hop Chinese COVID-19 dataset (called COKG-DATA for remembering) for COKG-QA based on the linked knowledge graph OpenKG-COVID19 launched by OpenKG, including comprehensive and representative information about COVID-19. COKG-QA achieves quite competitive performance in the 1-hop and 2-hop data while obtaining the best result with significant improvements in the 3-hop. And it is more efficient to be used in the QA system for users. Moreover, the user study shows that the system not only provides accurate and interpretable answers but also is easy to use and comes with smart tips and suggestions.
分类： 图书馆学、情报学 >> 图书馆学 提交时间： 2023-10-08 合作期刊: 《知识管理论坛》
摘要： [ 目的 / 意义 ] 对已有的文本表示、分类算法进行组合，遴选一种复杂度低、训练时间少的组合 方式，构建商品评论情感文本分类的优化模型。[ 方法 / 过程 ] 以 Keras API 为应用环境，将 Word2vec 词 向量输入 Embedding 嵌入层，依据句子词索引序列，通过控制 trainable 参数实现 3 种商品评论的文本表示； 将不同的文本表示分别与不同分类算法进行匹配，分析分类效果差异，确立较优算法组合。[ 结果 / 结论 ] Word2vec词向量输入Embedding嵌入层继续训练的文本表示方法，结合TextCNN算法训练获得的分类模型， 在商品评论测试集上分类效果表现较好，准确率和ROC曲线面积AUC值分别为94.02%、0.982 7。应用表明， 分类模型能较好实现商品评论的情感分类，有较好的分类泛化能力。
分类： 物理学 分类： 物理学 >> 基本粒子与场物理学 提交时间： 2016-12-28
摘要： We study the direct mediation of metastable supersymmetry breaking by a Φ2Φ2\Phi^2 (ΦΦ\Phi is the meson field) deformation to the ISS model and extend it by splitting ΦΦ\Phi into two parts and gauging the flavor symmetry. We find that with such an extensi
分类： 物理学 分类： 物理学 >> 基本粒子与场物理学 提交时间： 2016-12-28
摘要： We embed the minimal left-right model SU(2)_L\times SU(2)_R\times U(1)_{B-L} into an SU(4)_W gauge group, and break the unified group via five-dimensional S^1/(Z_2\times Z_2) orbifolding. Leptons are fitted into SU(4)_W multiplets and located on a symmetr
分类： 物理学 >> 基本粒子与场物理学 提交时间： 2016-05-15
摘要： We study the direct mediation of metastable supersymmetry breaking by a Phi(2)-deformation to the ISS model and extend it by splitting both Tr Phi and Tr Phi(2) terms in the superpotential and gauging the flavor symmetry. We find that with such an extension enough-long-lived metastable vacua can be obtained and the proper gaugino masses can be generated. Also, this allows for constructing a kind of models which can avoid the Landau pole problem. Especially, in our metastable vacua there exist a large region for the parameter m(3) which can satisfy the phenomenology requirements and allow for a low SUSY-breaking scale (h mu(2) similar to 100 TeV). Copyright (C) EPLA, 2009
点击量
待评议
点击量
下载量
评论
通过
