steve's repositories
ANCE
A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks
AutoAttention
Tensorflow implementaion for AutoAttention
autofaiss
Automatically create Faiss knn indices with the most optimal similarity search parameters.
bertviz
Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)
Co-Action-Network
Implementation of CAN: Revisiting Feature Co-Action for Click-Through RatePrediction
COSINE
This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach' (In Proc. of NAACL-HLT 2021).
DropoutNet
Code for the NeurIPS'17 paper "DropoutNet: Addressing Cold Start in Recommender Systems"
eeuen
code for "Addressing Exposure Bias in Uplift Modeling forLarge-scale Online Advertising"
FCPO
code for ‘Towards Long-term Fairness in Recommendation’
GraphiT
Official Pytorch Implementation of GraphiT
Graphormer
This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".
HCL
ICLR 2021, Contrastive Learning with Hard Negative Samples
LM-BFF
ACL'2021: LM-BFF: Better Few-shot Fine-tuning of Language Models
LOTClass
[EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach
meta-pseudo-labels
Unofficial TF2 implementation of "Meta Pseudo Labels" with linked metrics, dataset and models
MetaHIN
Source code for KDD 2020 paper "Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation"
MixGCF
MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems, KDD2021
MPL-pytorch
Unofficial PyTorch implementation of "Meta Pseudo Labels"
PDA
This is an implemention for our SIGIR 2021 paper "Causal Intervention for Leveraging Popularity Bias inRecommendation" based on tensorflow..
poeem
A library for end-to-end learning of embedding index and retrieval model
PoNet
Code for paper "PoNet: Pooling Network for Efficient Token Mixing in Long Sequences".
quince
Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
SeqMix
The repository for our EMNLP'20 paper SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup.
TLM
NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
wiki_zh_word2vec
利用Python构建Wiki中文语料词向量模型试验