cytsinghua Goto Github PK

data_diet

datnet

The implementation of Dual Adversarial Neural Transfer (DATNets) for Sequence Labeling, which is able to tackle sequence labeling tasks such as POS Tagging, NER, Chunking,etc..

decoupled_ner

deep-ctr-prediction

CTR prediction models based on deep learning(基于深度学习的广告推荐CTR预估模型)

deep-recommender-system

深度学习在推荐系统中的应用及论文小结。

deep_rec

存放推荐算法相关代码、文档、资料

deepctr

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

deepctr-torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

deepspeedexamples

Example models using DeepSpeed

delayedfeedback

dice_loss_for_nlp

The repo contains the code of the ACL2020 paper `Dice Loss for Data-imbalanced NLP Tasks`

diversity-based-generalization

Unsupervised Domain Adaptation in Text

domain-attention

codes for paper "Domain Attention Model for Multi-Domain Sentiment Classification"

domain_blse

Projecting Embeddings for Domain Adaptation: Joint Modeling of Sentiment in Diverse Domains

dssm

DSSM and Multi-View DSSM

duee_2020

2020语言与智能技术竞赛：事件抽取任务方案代码

dygiepp

Span-based system for named entity, relation, and event extraction.

elr

Official Implementation of Early-Learning Regularization Prevents Memorization of Noisy Labels

embedding_study

中文预训练模型生成字向量学习，测试BERT，ELMO的中文效果

epidemic-sentence-pair

天池 疫情相似句对判定大赛 线上第一名方案

euler

A distributed graph deep learning framework.

event_entity_coref_ecb_plus

A cross-document event and entity coreference resolution system, trained and evaluated on the ECB+ corpus.

event_extraction

baidu aistudio event extraction competition

eventcoref

eventextraction

Baidu lic 2020 event extraction

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

finetunezoo

简洁、方便、好用的BERT~finetune代码，LCQMC数据为例

fudan_mtl_reviews

TensorFlow implementation of the paper `Adversarial Multi-task Learning for Text Classification`

gat

Graph Attention Networks (https://arxiv.org/abs/1710.10903)