Stars
农业知识图谱(AgriKG):农业领域的信息检索,命名实体识别,关系抽取,智能问答,辅助决策
农业领域知识图谱的构建,包括数据爬取(百度百科)、数据分类、利用结构化数据生成三元组、非结构化数据的分句(LTP),分词(jieba),命名实体识别(LTP)、基于依存句法分析(主谓关系等)的关系抽取和利用neo4j生成可视化知识图谱
Learning graph embedding using DeepWalk or Node2Vec
This toolkit was designed for the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.
Pre-Training with Whole Word Masking for Chinese BERT(中文BERT-wwm系列模型)
State-of-the-Art Text Embeddings
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Codes for "TENER: Adapting Transformer Encoder for Named Entity Recognition"
Embedding, NMT, Text_Classification, Text_Generation, NER etc.
Lstm-crf,Lattice-CRF,bert-ner及近年ner相关论文follow
This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.
In this repository, I record the application of bert and bert multi-labels classification.
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.
自然语言处理(nlp),小姜机器人(闲聊检索式chatbot),BERT句向量-相似度(Sentence Similarity),XLNET句向量-相似度(text xlnet embedding),文本分类(Text classification), 实体提取(ner,bert+bilstm+crf),数据增强(text augment, data enhance),同义句同义词生成,句子…
code for EMNLP 2019 paper Text Summarization with Pretrained Encoders
对比TextRank和TF-IDF在关键词抽取上的不同,在数据量上,TextRank更适合单篇文本的关键词生成,TF-IDF则适合大语料下的关键词生成,在原理上不相同,TF-IDF为统计模型强调词权重,TextRank是利用局部词汇之间关系(共现窗口)对后续关键词进行排序,排序靠前的则适合做关键字
复现了论文《基于主题模型的短文本关键词抽取及扩展》的代码
利用Python实现中文文本关键词抽取,分别采用TF-IDF、TextRank、Word2Vec词聚类三种方法。
The Natural Language Decathlon: A Multitask Challenge for NLP
An open-source NLP research library, built on PyTorch.