Code for the paper "It's Not Easy Being Wrong: Evaluating Process of Elimination Reasoning in Large Language Models"

A game theoretic approach to explain the output of any machine learning model.

Inference code for Llama models

Resources for our NAACL 2022 paper on revisiting partial-input baselines.

Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models @ EACL 2023

Diverse Natural Language Inference Collection - NLI dataset that can used to evaluate how well models perform distinct types of reasoning (EMNLP 2018)

Repository for the implementation and evaluation of DD-GloVe, a train-time debiasing algorithm to learn GloVe word embeddings by leveraging dictionary definitions.

ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.

This repository contains code for RIFLE implementation using Paddle.

Latex code for making neural networks diagrams

Papers on fairness in NLP

An open-source NLP research library, built on PyTorch.

There was no free Dictionary API on the web when I wanted one for my friend, so I created one.

An implementation of GloVe in TensorFlow

InterpretDL: Interpretation of Deep Learning Models，基于『飞桨』的模型可解释性算法库。

Dict2vec is a framework to learn word embeddings using lexical dictionaries.

Distributed skipgram mixture model for multisense word embedding

NAACL 2019 (Oral): Code for "Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings"

[DEPRECATED] Repo for exploring multi-task learning approaches to learning sentence representations

Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings

Code for the paper "Language Models are Unsupervised Multitask Learners"

Google Research

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)【安全加固，暂停交互，请耐心等待】

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

Tensorflow implementation of Product-based Neural Networks. An extended version is at https://github.com/Atomu2014/product-nets-distributed.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

3.8% and 18.3% on CIFAR-10 and CIFAR-100