本文前置知识: Pytorch基本操作 Word2Vec Pytorch实现: Skip-Gram本文用Pytorch实现了Skip - Gram, 它是Word2Vec的其中一种. 本文实现参考PyTorch 实现 Word2Ve

本文前置知识: BERT(详见ELMo, GPT, BERT) RoBERTa: A Robustly Optimized BERT Pretraining Approach本文是论文RoBERTa: A Robustly Opti

本文前置知识: AlexNet(详见卷积神经网络发展史) Attention(详见Seq2Seq和Attention) TransE(详见TransE: Translating Embeddings for Modeling Multi

TransE: Translating Embeddings for Modeling Multi-relational Data本文是论文Translating Embeddings for Modeling Multi-relation

本文前置知识: Self - Attention BERT 2020.11.17: 解决了标签泄露的疑惑. 2021.04.09: 修正可视化实验的描述. CoKE: Contextualized Knowledge Graph E

本文前置知识: ConvE Conv1d 2021.03.15: 指出权重共享并没有出现在源码中. A Novel Embedding Model for Knowledge Base Completion Based on Con

本文前置知识: ConvE Depth - wise Convolution 2020.11.14: 对实验进行部分补充. InteractE: Improving Convolution-based Knowledge Graph

CoLAKE: Contextualized Language and Knowledge Embedding 本文前置知识: BERT Self - Attention 2020.11.11: 想通了CoLAKE在训练时最关键的部分.

本文前置知识: 膨胀卷积(空洞卷积) 残差连接 Knowledge Graph Embedding with Atrous Convolution and Residual Learning本文是论文Knowledge Graph

本文前置知识: Transformer(Masked Self - Attention和FFN) BERT(与XLNet做对比) Seq2Seq(AutoRegressive & AutoEncoding) 2020.10.2

本文的前置知识: RNN Transformer Language Model ELMo, GPT, BERT本文是对ELMo, GPT, BERT三个模型的结构介绍以及个人理解, 多图预警. Introduction由于NLP领域

2020.10.03: 因torch版本更新, 对gather描述进行了修正. 2021.03.11: 更新了对gather的描述. Pytorch学习: 张量进阶操作整理内容顺序来自龙龙老师的<深度学习与PyTorch入门实战教