Skip to content
#

chinese

Here are 256 public repositories matching this topic...

nacyzhaomin
nacyzhaomin commented Mar 2, 2018

您好~
最近看rasa_nlu官方文档,上面写pipline有多种选择方式,除了作者您描述的两种以外,有一种推荐是:
Best for most: spaCy + sklearn
问题是:这个组合+jieba能用来处理中文吗?不了解spaCy,所以想问问作者,当初为什么选择jieba+mitie+sklearn。而不是上面这种组合呢?谢谢

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

  • Updated May 6, 2020
  • Python

基于Pytorch和torchtext的自然语言处理深度学习框架,包含序列标注、文本分类、句子关系、文本生成、结构分析、五大功能模块,已实现了命名实体识别、中文分词、词性标注、语义角色标注、情感分析、关系抽取、语言模型、文本相似度、文本蕴含、依存句法分析、词向量训练、聊天机器人、机器翻译、文本摘要等功能。框架功能丰富,开箱可用,极易上手!基本都是学习他人实现然后自己修改融合到框架中,没有细致调参,且有不少Bug~

  • Updated Jan 10, 2020
  • Python
AlucardNosferatu
AlucardNosferatu commented Nov 30, 2019

It tell me the rasa_nlu.train is obsolete and I change it to rasa.nlu.train as being told by cmd, then it said that rasa.nlu.train should not be run directly, and I follow its advice and change it to rasa train, this time it told me --path and --project is redundant and so I remove them, then it told me that the config.yml the command specified lack mandatory param called "policies", now I dont kn

Improve this page

Add a description, image, and links to the chinese topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the chinese topic, visit your repo's landing page and select "manage topics."

Learn more

You can’t perform that action at this time.