Liang Pang's repositories
MatchPyramid-TensorFlow
A simple version of MatchPyramid implement in TensorFlow. Paper https://arxiv.org/abs/1602.06359.
textnet-release
TextNet: A deep neural network framework for text matching
DeepRank_PyTorch
A simple version of DeepRank & MatchPyramid implemented in PyTorch.
textnet-model
The models run on Textnet.
wsdm2021-beyond-prp-tutorial
WSDM2021 Tutorial: Beyond Probability Ranking Principle: Modeling the Dependencies among Documents
IntegratedGradients
Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework.
acl2020-openqa-tutorial
ACL2020 Tutorial: Open-Domain Question Answering
caffe
Caffe: a fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.
Deep-Listwise-Context-Model-for-Ranking-Refinement
A Tensorflow implementation of the Deep Listwise Context Model (DLCM) for ranking refinement.
Integrated-Gradients
Attributing predictions made by the Inception network using the Integrated Gradients method
IntegratedGradientsTF
Tensorflow implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks". It explains connections between two tensors.
models
Models and examples built with TensorFlow
np_analysis
Adversarial attacks generated for the ACL paper "Did the Model Understand the Question?"
Ordered-Neurons
Code for the paper "Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks"
PertMap
Python code for perturbation-based saliency map
playground
PlayGround: AI Research into Multi-Agent Learning.
pyltr
Python learning to rank (LTR) toolkit
tensorforce
TensorForce: A TensorFlow library for applied reinforcement learning
transformer
A TensorFlow Implementation of the Transformer: Attention Is All You Need
tutorials2018
tutorials for the ML course
UbuntuDataGenerator
A modify version from [Ubuntu-Dialogue-Generationv2](https://github.com/ryan-lowe/Ubuntu-Dialogue-Generationv2). Fix the positive and negative sentence length bias.
ULTRA
Unbiased Learning To Rank Algorithms (ULTRA)