hitalex

mmbt

Supervised Multimodal Bitransformers for Classifying Images and Text

NREPapers

Must-read papers on neural relation extraction (NRE)

attention

some attention implements

Awesome-Chinese-NLP

A curated list of resources for Chinese NLP 中文自然语言处理相关资料

BDCI2019-SENTIMENT-CLASSIFICATION

CCF BDCI 2019 互联网新闻情感分析 复赛top1解决方案

bert

TensorFlow code and pre-trained models for BERT

bert-sequence-tagging

基于BERT的中文序列标注

CCF-BDCI-Sentiment-Analysis-Baseline

The code for CCF-BDCI-Sentiment-Analysis-Baseline

CEC-Corpus

:books:中文突发事件语料库（Chinese Emergency Corpus）-上海大学-语义智能实验室

Chinese-Word-Vectors

100+ Chinese Word Vectors 上百种预训练中文词向量

CIKM-Cup-2017

CIKM AnalytiCup 2017: Short-Term Precipitation Forecasting Based on Radar Reflectivity Images

ConfliBERT

ConfliBERT: A Pre-trained Language Model for Political Conflict and Violence (NAACL 2022)

datastories-semeval2017-task4

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".

DeepIE

DeepIE: Deep Learning for Information Extraction

eda_nlp

Code for the EMNLP-IJCNLP paper: Easy data augmentation techniques for boosting performance on text classification tasks.

Entity-Relation-Extraction

Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取，2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019

fnc-1

Fake News Challenge

GPT-4-LLM

LLMSurvey

A collection of papers and resources related to Large Language Models.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Research

novel deep learning research works with PaddlePaddle

sentiment_analysis_textcnn

stopwords-1

中文常用停用词表（哈工大停用词表、百度停用词表等）

text_classification

all kinds of text classification models and more with deep learning

tsd

Target-specific Stance Detection

TwiBot-22

Offical repository of TwiBot-22.

WSDM-Cup-2019

[ACM-WSDM] 3rd place solution at WSDM Cup 2019, Fake News Classification on Kaggle.

wsdm19cup

My 1st place solution at WSDM 2019 cup for fake news classification

WSDM2019

WSDM Cup 2019 Fake News Classification - 2nd place

XLM

PyTorch original implementation of Cross-lingual Language Model Pretraining.