Personal website

使用TensorFlow实现对知识图谱的表征学习，包括transe\transd\transh\transr

An implementation of TransE and its extended models for Knowledge Representation Learning on TensorFlow

简洁易用版TinyBert：基于Bert进行知识蒸馏的预训练语言模型

Source code and dataset for KDD 2020 paper "Controllable Multi-Interest Framework for Recommendation"

Source code and dataset for KDD 2020 paper "Controllable Multi-Interest Framework for Recommendation"

✏️ 算法相关知识储备 LeetCode with Python and JavaScript 📚

Data Structure and Algorithm notes. 数据结构与算法/leetcode/lintcode题解/

Python & JAVA Solutions for Leetcode

欢迎加QQ群：109764489，贡献力量！

Implementation and experiments of graph neural netwokrs, like gcn,graphsage,gat,etc.

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

Code for the IJCAI'19 paper "Deep Session Interest Network for Click-Through Rate Prediction"

简单粗暴 TensorFlow 2 | A Concise Handbook of TensorFlow 2 | 一本简明的 TensorFlow 2 入门指导教程

深度学习入门开源书，基于TensorFlow 2.0案例实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.

A cloud-native vector database, storage for next generation AI applications

Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

Code for the paper "Contextual and Sequential User Embeddings for Large-Scale Music Recommendation".

Python SDK for Milvus.

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

A library for efficient similarity search and clustering of dense vectors.

A curated list of awesome JupyterLab extensions and resources

This project compares several methods for finding similar sentences, including Jaccard similarity, TF-IDF, GloVe, BERT, and RoBERTa.

Example code on using bert-as-service to analyze sentences.

Using BERT and Cosine Similarity for testing similarity of legal paragraphs

Finding similar sentences between documents using Bidirectional Encoder Representation from Transformers (BERT) and Universal Sentence Encoder (USE)

使用开源的Bert-as-Service预训练生成文档特征向量，基于k-means对COVID-19文献聚类，t-SNE可视化数据，通过LDA为每个簇生成主题关键词，画Bokeh图实现按簇、关键词搜索和筛选数据。