[深度学习] Building Knowledge Graphs About Political Agents in the AgeofMisinformation.pdf

说明： Abstract. This paper presents the construction of a Knowledge Graph about relations between agents in a political system. It discusses the main modeling challenges, with emphasis on the issue of trust and provenance. Implementation decisions are als
<qq_31367595> 上传 | 大小：1mb

[深度学习] Binarized Knowledge Graph Embeddings.pdf

说明： Abstract. Tensor factorization has become an increasingly popular approach to knowledge graph completion (KGC), which is the task of automatically predicting missing facts in a knowledge graph. However, even with a simple model like CANDECOMP/PARAFA
<qq_31367595> 上传 | 大小：214kb

[深度学习] Be Concise and Precise：SynthesizingOpen-DomainEntity Descriptions from Facts.pdf

说明： Despitebeingvastrepositoriesoffactualinformation,cross-domain knowledgegraphs,suchasWikidataandtheGoogleKnowledge Graph, only sparsely provide short synoptic descr iptions for entities.Suchdescr iptionsthatbrieflyidentifythemostdiscernible featureso
<qq_31367595> 上传 | 大小：1mb

[深度学习] An End-to-End Network for Generating Social Relationship Graphs.pdf

说明： Socially-intelligent agents are of growing interest in artificial intelligence. To this end, we need systems that can understand social relationships in diverse social contexts. Inferring the social context in a given visual scene not only involves r
<qq_31367595> 上传 | 大小：7mb

[深度学习] Advancing the State of the Art in Open Domain Dialog Systems the Alexa Prize.pdf

说明： Building open domain conversational systems that allow users to have engaging conversations on topics of their choice is a challenging task. Alexa Prize was launched in 2016 to tackle the problem of achieving natural, sustained, coherent and engagin
<qq_31367595> 上传 | 大小：1mb

[深度学习] A tensorized logic programming language for large-scale data.pdf

说明： We introduce a new logic programming language T-PRISM based on tensor embeddings. Our embedding scheme is a modification of the distribution semantics in PRISM, one of the state-of-the-art probabilistic logic programming languages, by replacing distr
<qq_31367595> 上传 | 大小：117kb

[深度学习] A Relational Tucker Decomposition for Multi-Relational Link Prediction.pdf

说明： We propose the Relational Tucker3 (RT) decomposition for multi-relational link prediction in knowledge graphs. We show that many existing knowledge graph embedding models are special cases of the RT decomposition with certain predefined sparsity patt
<qq_31367595> 上传 | 大小：888kb

[深度学习] Trust and Privacy in Knowledge Graphs.pdf

说明： This paper presents the KG Usage framework, which allows the introduction of KG features to support Trust, Privacy and Transparency concerns regarding the use of its contents by applications. A real-world example is presented and used to illustrate
<qq_31367595> 上传 | 大小：376kb

[深度学习] 周光有-面向大规模知识图谱的智能问答.pdf

说明： 知识图谱旨在描述真实世界中存在的各种实体或概念 及其关系,其构成一张巨大的语义网络图，节点表示实 体或概念，边则由属性或关系构成。
<qq_31367595> 上传 | 大小：2mb

[深度学习] 微博情感分析语料.rar

说明： 谷歌Google 中文BERT中文预训练模型 chinese_L-12_H-768_A-12.zip。BERT本质上是一个两段式的NLP模型。第一个阶段叫做：Pre-training，跟WordEmbedding类似，利用现有无标记的语料训练一个语言模型。第二个阶段叫做：Fine-tuning，利用预训练好的语言模型，完成具体的NLP下游任务。可以测试对这个语料库进行分析。
<u010243662> 上传 | 大小：1mb

[深度学习] 文本识别数据集SVT.zip

说明： 文本识别数据集：SVT 训练集257张 测试集647 标签中都是每张图片上对应的单词 train.txt和test.txt都是过滤之后的标签（去掉符号和小于3个字符的） 另外两个标签是原版标签没有进行任何过滤 可自行在前面添加文件路径，也可以去我的主页下载添加路径的代码文件（python文件）
<weixin_43136911> 上传 | 大小：5mb

[深度学习] 文本识别数据集IIIT.zip

说明： 文本识别数据集：IIIT 训练集2000张 测试集3000 标签中都是每张图片上对应的单词 train.txt和test.txt都是过滤之后的标签（去掉符号和小于3个字符的） 另外两个标签是原版标签没有进行任何过滤 可自行在前面添加文件路径，也可以去我的主页下载添加路径的代码文件（python文件）
<weixin_43136911> 上传 | 大小：93mb