chenmoshushi

ERNIE-1

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

KnowledgeGraphData

史上最大规模1.4亿中文知识图谱开源下载

albert_zh

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

tianchi-nl2sql-top1

天池nl2sql冠军方案

tensorflow_ernie

将百度ernie的paddlepaddle模型转成tensorflow模型

roberta_zh

RoBERTa中文预训练模型: RoBERTa for Chinese

ERNIE-Pytorch

ERNIE Pytorch Version

coling2018-graph-neural-networks-question-answering

Accompanying code for our COLING 2018 paper "Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering"

adversarial

Code and hyperparameters for the paper "Generative Adversarial Networks"

StackPropagation-SLU

Open source code for EMNLP-19 Paper "A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding".

bert_distill

BERT distillation（基于BERT的蒸馏实验 ）

Chinese-PreTrained-XLNet

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

PreSumm

code for EMNLP 2019 paper Text Summarization with Pretrained Encoders

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

bertviz

Tool for visualizing attention in the Transformer model (BERT, GPT-2, XLNet, and RoBERTa)

metric-learn

Metric learning algorithms in Python

MASS

MASS: Masked Sequence to Sequence Pre-training for Language Generation

FixRes

This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423

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。

bert_score

BERT score for text generation

AdversarialNetsPapers

The classical paper list with code about generative adversarial nets

neural-template-gen

pytext

A natural language modeling framework based on PyTorch

grpc

The C based gRPC (C++, Python, Ruby, Objective-C, PHP, C#)

tutorials-1

Tutorials for creating and using ONNX models

landslide

Generate HTML5 slideshows from markdown, ReST, or textile

tensorflow_practice

tensorflow实战练习，包括强化学习、推荐系统、nlp等

xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Chinese-BERT-wwm

Pre-Training with Whole Word Masking for Chinese BERT