yty3805595

dstc

Dialog State Tracking Challenge 2 & 3 Data

PaddlePaddle-Knover

Knover的使用教程，用以训练一个完整的PLATO-2模型，还包括了两个快速实现多轮对话的现成模块。A manual to use Knover to train Plato-2, including two modules to achieve bot-dialog.

LetsGoDataset

This repository makes the integral Let's Go dataset publicly available.

boto3

AWS SDK for Python

Knover

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

allennlp

An open-source NLP research library, built on PyTorch.

CS-Notes

:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

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scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

jina

☁️ Build multimodal AI applications with cloud-native stack

text_scalpel

Modify Chinese text, modified on LaserTagger Model. I name it "文本手术刀".目前，本项目实现了一个文本复述任务，用于NLP语料的数据增强。

google-research

Google Research

multiwoz

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

d2l-zh

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

d2l-pytorch

This project reproduces the book Dive Into Deep Learning (https://d2l.ai/), adapting the code from MXNet into PyTorch.

MNN

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

lasertagger-chinese

lasertagger-chinese；lasertagger中文学习案例，案例数据，注释，shell运行

python-pinyin

汉字转拼音(pypinyin)

ChineseTone

[本项目不再维护] 将汉字转换为拼音， 支持多音字，拼音 -> pin yin

text-classification-cnn-rnn

CNN-RNN中文文本分类，基于TensorFlow

delta

DELTA is a deep learning based natural language and speech processing platform.

named_entity_recognition

中文命名实体识别（包括多种模型：HMM，CRF，BiLSTM，BiLSTM+CRF的具体实现）

BertBasedCorrectionModels

PyTorch impelementations of BERT-based Spelling Error Correction Models. 基于BERT的文本纠错模型，使用PyTorch实现。

Synonyms

:herb: 中文近义词：聊天机器人，智能问答工具包

synonym_detection

Mining synonyms from unstructured and semi-structured data

kenlm

KenLM: Faster and Smaller Language Model Queries

lasertagger

BERT-flow

TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)

GPT2-Chinese

Chinese version of GPT2 training code, using BERT tokenizer.

qlib

Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.

ltp

Language Technology Platform