Pinned Repositories
jiant
jiant is an nlp toolkit
nlu-test-sets
Analysis of NLU test sets with IRT
PRPN-Analysis
This repo contains the analysis results reported in the paper "Grammar Induction with Neural Language Models: An Unusual Replication"
awesome-deep-learning
A curated list of awesome Deep Learning tutorials, projects and communities.
bert_trees
cs6101
NUS CS6101 : Deep Learning for NLP (which is based on Richard Socher's Stanford CS244D)
explore-myanmar-covid19-data
GDGYangon
Code Examples for my presentation at GDG DevFest Yangon. Presentation Slides can be found at https://goo.gl/aU60Zd .
ThisAndThat
Code Examples for CNY codejam.
phu-pmh's Repositories
phu-pmh/explore-myanmar-covid19-data
phu-pmh/bert_trees
phu-pmh/compare-mt
A program to compare language generation results and extract salient features
phu-pmh/DataScienceCourse
This holds iPython notebooks and lecture slides for the Intro to Data Science Master's course I teach at NYU.
phu-pmh/DeepRL-Agents
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
phu-pmh/DS-GA-1011-Fall2017
DS-GA-1011 Natural Language Processing with Representation Learning
phu-pmh/error-repair-parsing
Error-repair Dependency Pasring for Ungrammatical Texts (ACL 2017)
phu-pmh/event-jekyll-theme
Jekyll Theme package for your event
phu-pmh/fairseq-1
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
phu-pmh/generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
phu-pmh/grayscale-theme
Jekyll theme based on Grayscale Start Bootstrap theme
phu-pmh/InferSent
Sentence embeddings (InferSent) and training code for NLI.
phu-pmh/ir17
phu-pmh/irt-leaderboard
Leaderboards are widely used in NLP and push the field forward. While leaderboards are a straightforward ranking of NLP models, this simplicity can mask nuances in evaluation items (examples) and subjects (NLP models). Rather than replace leaderboards, we advocate a re-imagining so that they better highlight if and where progress is made. Building on educational testing, we create a Bayesian leaderboard where latent subject skill and latent item difficulty predict correct responses. Using this model, we analyze the reliability of leaderboards. Afterwards, we show the model can guide what annotate, identify annotation errors, detect overfitting, and identify informative examples.
phu-pmh/judge_embedding
phu-pmh/lm_evaluation_harness
phu-pmh/mac-dev-setup
A beginner's guide to setting up a development environment on Mac OS X
phu-pmh/myanmar-covid19-data
A collection of open data produced by government and non-government organizations and volunteers relevant to Covid-19 response in Myanmar
phu-pmh/nyu-ai-workshop
Awesome conference website in 5 minutes.
phu-pmh/online-meta
Meta-learning
phu-pmh/OpenNMT-py
Open Source Neural Machine Translation in PyTorch
phu-pmh/Ordered-Neurons
Code for the paper "Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks"
phu-pmh/PRPN
Parsing Reading Predict Network
phu-pmh/py-irt
Bayesian IRT models in Python
phu-pmh/pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
phu-pmh/QueryReformulator
phu-pmh/spinn
NYU ML² work on SPINN-based sentence encoders
phu-pmh/the-incredible-pytorch
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
phu-pmh/unsupervised-treelstm
phu-pmh/UnsupervisedMT
Phrase-Based & Neural Unsupervised Machine Translation