Piji Li

App-DL. Deep Learning and applications in Startups, CV, NLP

AIStartups. Startups about artificial intelligence. (DM, ML, NLP, CV...)

SongNet. Code for ACL 2020 paper "Rigid Formats Controlled Text Generation"：https://www.aclweb.org/anthology/2020.acl-main.68/

neural-summ-cnndm-pytorch. Neural abstractive summarization (seq2seq + copy (or pointer network) + coverage) in pytorch on CNN/Daily Mail

Guyu. Chinese GPT2: pre-training and fine-tuning framework for text generation

TranSummar. Transformer for abstractive summarization on cnn/daily-mail and gigawords

JRNN. LSTM and GRU in JAVA

PG_BOW_DEMO. Image Classification using Bag of Words and Spatial Pyramid BoW

hierarchical-encoder-decoder. Hierarchical encoder-decoder framework for sequences of words, sentences, paragraphs and documents using LSTM and GRU in Theano

TtT. code for ACL2021 paper "Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction"

PG_Curve. Matlab code for computing and visualization: Confusion Matrix, Precision/Recall, ROC, Accuracy, F-Measure etc. for Classification.

rnn-theano. RNN(LSTM, GRU) in Theano with mini-batch training; character-level language models in Theano

PG_DEEP. demo of deep belief nets

variational-autoencoder-theano. Variational Autoencoders (VAEs) in Theano for Images and Text

DRGD-LCSTS. code for "Deep Recurrent Generative Decoder for Abstractive Text Summarization"

dialogue-hred-vhred. HRED VHRED VHCR for Multi-Turn Dialogue Systems

lipiji.github.io. HTML

datasets. datasets for NLP research

HFT. code:Hidden factors and hidden topics: Understanding rating dimensions with review text.

neural-summ-reproduce-lcsts-pytorch. Abstractive summarization on LCSTS dataset

uChecker. Code of the COLING22 paper "uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers"

rnn-pytorch. study pytorch

NRT-theano. Code for our SIGIR'2017 paper "Neural Rating Regression with Abstractive Tips Generation for Recommendation"

data-summ-cnn_dailymail. non-anonymized cnn/dailymail dataset for text summarization

JLBFGS. Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) in Java

PG_PageRank. pagerank using mapreduce format

vae-salience. "Salience Estimation via Variational Auto-Encoders for Multi-Document Summarization"

PG_PLSA. plsa demo in python

neural-dialogue-s2s-weibo-py3. Python

world2vec. Pre-trained word and phrase vectors

Firefly. Firefly: 大模型训练工具，支持训练Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

t5_summarization. Python

neural-topic-model. neural topic model based on VAE - theano

language_model_transformer. language model via transformer

jilp. Java ILP is a simplified java interface to (mixed) integer linear programming solvers like, e.g., lp_solve, Glpk, SAT4J (0-1 ILP), CPLEX, or Mosek.

stopwords.

vae-salience-ramds. "Reader-Aware Multi-Document Summarization: An Enhanced Model and The First Dataset"

gan-bow-text. Generative Adversarial Network (GAN) for text modeling

LeetCode. :pencil: Python / C++ 11 Solutions of All 468 LeetCode Questions

bert_zh_open200g_wordpiece. Python

LLaMA-Factory. Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

collaborative-topic-regression. C++

TopCJ. Top Conference Timeline

cws-seq2seq. Chinese Word Segment using Seq2Seq Framework.

PG_ROC_PR_R. ROC and PR curve using R

Chinese_medical_NLP. 中文医疗NLP领域 数据集，论文 ，知识图谱，语料，工具包

SwarmRank. Particle Swarm Optimization for Classification and Recommender Systems

water_level_prediction. Python

TextAdventure.

adversarial-variational-autoencoders. Adversarial Variational Auto-Encoders (AVAEs) in Theano

ChatAlpaca. A Multi-Turn Dialogue Corpus based on Alpaca Instructions

FindTheChatGPTer. ChatGPT爆火，开启了通往AGI的关键一步，本项目旨在汇总那些ChatGPT的开源平替们，包括文本大模型、多模态大模型等，为大家提供一些便利

PATG. Code for WWW2019 paper "Persona-Aware Tips Generation"

FedML. FedML: A Research Library and Benchmark for Federated Machine Learning

POT. POT : Python Optimal Transport

textrank_keyword_summary. textrank based keywords extraction and summarization

tianya-docs. 精心收集的天涯神贴，不带水印，方便阅读