zhyan567 Goto Github PK

ark-nlp

A private nlp coding package, which quickly implements the SOTA solutions.

asset_class_detection_for_mutual_funds_using_nlp

This project proposes to determine the accurate asset class of the fund based on its description. The project starts from scraping principal investment strategies of American mutual funds from US Securities and Exchange Commission (SEC). Afterward, we did some data cleaning and data exploration. Finally, We implement machine learning (Naive Bayesian, K-Nearest Neighbors, and Random Forest) and deep learning algorithms (LSTM and Bert) to train and predict the corresponding asset class, using the asset class provided by Bloomberg as a label.

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合

bert4keras

keras implement of transformers for humans

bert_seq2seq

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。

bilstm_crf_sequence_labeling_pytorch

Bi-LSTM+CRF sequence labeling model implemented in PyTorch

chatbot

一个可以自己进行训练的中文聊天机器人， 根据自己的语料训练出自己想要的聊天机器人，可以用于智能客服、在线问答、智能聊天等场景。目前包含seq2seq、seqGAN版本、tf2.0版本、pytorch版本。

cluener2020

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

daga

Data Augmentation with a Generation Approach for Low-resource Tagging Tasks

dgk_lost_conv

dgk_lost_conv 中文对白语料 chinese conversation corpus

gpt2-chinese

Chinese version of GPT2 training code, using BERT tokenizer.

kdconv

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation

learngit2

pretrained-language-model

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

seq2seq_chatbot_qa

使用TensorFlow实现的Sequence to Sequence的聊天机器人模型

startgit

stbp-for-training-spikingnn

Spatio-temporal BP for SNNs