zhusy09's repositories
chinese-poetry
最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。
Chinese_segment_augment
python3实现互信息和左右熵的新词发现
DeepTweets
Fine tuned GPT-2 with tweets from Black Twitter in attempt to auto generate funny tweets. Idea inspired by Lex Fridman
Don-AI-ld-Trump
gpt2 Colab Notebook and Dataset + Model to Generate Fake Trump Tweets
Fake-Trump-Tweet
A model to generate Fake Trump Tweets, which says "RealDonaldTrump" a lot!!!
fake_trump_tweet
Tweet Classifiers using Multinomial Naive Bayes and LSTM + Tweet Generators using Markov Chain and LSTM = the Most Trumpy (fake) Tweets
fucking-algorithm
手把手撕LeetCode题目，扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.
gpt-2-simple
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
make-lstm-great-again
Donald Trump's tweets generator
New-Word-Detection
新词发现算法(NewWordDetection)
New-Word-Discovery
新词发现 基于词频、凝聚系数和左右邻接信息熵
New_word_discovery
中文新词发现
nlp_chinese_corpus
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
py-kenlm-model
python | 高效使用统计语言模型kenlm：新词发现、分词、智能纠错等
pycorrector
pycorrector is a toolkit for text error correction. It was developed to facilitate the designing, comparing, and sharing of deep text error correction models.
semantic-guesser
Training and testing of linguistic passwords models.
Swifter.Json
A powerful, easy-to-use and fastest json serializer and deserializer on .Net platforms.
tensorflow-1.4-billion-password-analysis
Deep Learning model to analyze a large corpus of clear text passwords.
trump-tweet-archive
trump twitter archive
Trump-Tweet-Generator
A project to finetune a GPT-2 338M model on US President Donald Trump's twitter feed, along with a basic Flask website to display some generated outputs from the model.
word-discovery
速度更快、效果更好的中文新词发现