yongzhuo / nlp_xiaojiang
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,句子主干提取(mainpart),中文汉语短文本相似度,文本特征工程,keras-http-service调用
☆1,531Updated 3 years ago
Alternatives and similar repositories for nlp_xiaojiang:
Users that are interested in nlp_xiaojiang are comparing it to the libraries listed below
- 一行代码使用BERT生成句向量,BERT做文本分类、文本相似度计算☆1,658Updated 5 years ago
- 基于知识图谱的问答系统,BERT做命名实体识别和句子相似度,分为online和outline模式☆1,462Updated 3 years ago
- 中文长文本分类、短句子分类、多标签分类、两句子相似度(Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short),字词句向量嵌入层(…☆1,796Updated 8 months ago
- 使用预训练语言模型BERT做中文NER☆937Updated 4 years ago
- An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。☆1,365Updated 2 years ago
- Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard☆1,775Updated 2 years ago
- CLUENER2020 中文细 粒度命名实体识别 Fine Grained Named Entity Recognition☆1,468Updated 2 years ago
- Collections of Chinese NLP corpus☆890Updated 4 years ago
- A concept and obvious expression pattern collection of Chinese compound event extraction which then be evolved into ComplexEventGraph,本项目…☆1,198Updated 6 years ago
- Pre-Trained Chinese XLNet(中文XLNet预训练模型)☆1,650Updated last year
- bert中文分类实践☆735Updated 6 years ago
- 中文命名实体识别,实体抽取,tensorflow,pytorch,BiLSTM+CRF☆1,421Updated 4 years ago
- 今日头条中文新闻(文本)分类数据集☆368Updated 3 years ago
- 谷歌自然语言处理模型BERT:论文解析与python代码☆844Updated 6 years ago
- Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取,2019语言与 智能技术竞赛信息抽取任务解决方案。Schema based Knowledge …☆1,229Updated 4 years ago
- Open Chinese Language Pre-trained Model Zoo☆978Updated 4 years ago
- Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取☆2,242Updated last year
- 基于Pytorch和torchtext的自然语言处理深度学习框架。☆826Updated 4 years ago
- RoBERTa中文预训练模型: RoBERTa for Chinese☆2,667Updated 6 months ago
- A neural network model for Chinese named entity recognition☆1,791Updated 6 years ago
- pytorch实现 Bert 做seq2seq任务,使用unilm方案,现在也可以做自动摘要,文本分类,情感分析,NER,词性标注等任务,支持t5模型,支持GPT2进行文章续写。☆1,292Updated 2 years ago
- A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)☆2,333Updated 2 years ago
- Text Content Grapher based on keyinfo extraction by NLP method。输入一篇文档,将文档进行关键信息提取,进行结构化,并最终组织成图谱组织形式,形成对文章语义 信息的图谱化展示。☆1,394Updated 3 years ago
- 基于金融-司法领域(兼有闲聊性质)的聊天机器人,其中的主要模块有信息抽取、NLU、NLG、知识图谱等,并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口☆1,287Updated 3 years ago
- 自然语言处理工具Macropodus,基于Albert+BiLSTM+CRF深度学习网络架构,中文分词,词性标注,命名实体识别,新词发现,关键词,文本摘要,文本相似度,科学计算器,中文数字阿拉伯数字(罗马数字)转换,中文繁简转换,拼音转换。tookit(tool) of N…☆659Updated last year
- fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具,像spacy一样调用方便。☆753Updated last year
- An experiment and demo-level tool for text information extraction (event-triples extraction), which can be a route to the event chain an…☆925Updated 2 years ago
- 综合了同义词词林扩展版与知网(Hownet)的词语相似度计算方法,词汇覆盖更多、结果更准确。☆724Updated 3 years ago
- 复盘所有NLP比赛的TOP方案,只关注NLP比赛,持续更新中!☆2,709Updated 2 months ago
- DeepIE: Deep Learning for Information Extraction☆1,944Updated 2 years ago