scottishfold007 Goto Github PK

bert_seq2seq

pytorch实现bert做seq2seq任务，使用unilm方案,现在也可以做文本分类，情感分析等NLU任务。

bible_text_gcn

Text-Based Graph Convolution Network

blog20120

sdada

blurr

A library that integrates huggingface transformers with version 2 of the fastai framework

c-cnn-for-chinese-sentiment-analysis

基于字符级卷积神经网络的细粒度的中文情感分析以及具体的应用，使用flask restful做出的后端服务化，具体的项目细节和讲解看右面的ppt

causalcollocation

CausalKnowledgeBase, causal knowledge base including causal pairs extracted from web text using the methods like PMI, Collocation。基于网络文本的因果知识库项目，采用PMI，搭配抽取等方法，形成因果对频繁集。

causality

Tools for causal analysis

char_featurizer

汉字字符特征提取工具，可以提取出字符中的字音（声母、韵母、声调）、字形（偏旁、部首）、四角编码等特征，同时可作为tensor输入到模型

chars2vec

Character-based word embeddings model based on RNN for handling real world texts

chindia

2017 DF,CCF大数据与计算智能大赛——“中印对峙事件舆情分析”赛题全网数据

chinese-knowledge-triples-extraction

bootstrap式知识三元组抽取 开放式实体关系抽取 依靠依存分析确定可能的实体和关系

chinese-opinion-target-extraction

Pytorch implementation of "Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction", ACML2018

chinese_article_generate_2

chinese_keyphrase_extractor

A tool for chinese keyphrase extraction 一个快速从中文里抽取关键短语的工具，只消耗35M内存

chinese_ulmfit

中文ULMFiT 情感分析 文本分类

chinesehumorsentiment

ChineseHumorSentiment, chinese humor sentiment mining including corpus build and mining nlp methods.中文文本幽默情绪计算项目,项目包括幽默文本语料库的构建,幽默计算模型,包括幽默等级识别,幽默类型识别,隐喻类型识别,隐喻情绪识别等,语言是幽默的,NLP也应该是幽默的.

chinesenlpcorpus

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

chinesenounphraseextraction

使用词性模板抽取中文语料中的名词短语

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels

co-occurrence-matrix

使用Python构建共现矩阵，并以三元组形式存储到csv文件。

compare

A way of using Multiple Correspondence analysis to analyse Web Archives

conv-emotion

This repo contains implementation of different architectures for emotion recognition in conversations

corex_topic

Hierarchical unsupervised and semi-supervised topic models for sparse count data with CorEx

ctripscrapy

携程旅游景点爬虫

czech_textual_networks

This repository contains script for generation, analysis and visualization of word co-occurrence networks from texts in Czech. It includes functions for language data preprocessing, especially lemmatization and POS-tagging .

datainbrief

a complete data infrastructure with collection, cleaning, storage, visualization, search, machine learning models, web servers, APIs, and caching.

declutr

The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!

deeplearning-500-questions

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

deeplearning-resources

many wonderful deep learning Resources~

deeplearningbook-notes

Notes on the Deep Learning book from Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)