Starred repositories
GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition
Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
Code for ACL 2021 main conference paper "Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances".
Short Course - Applied Machine Learning for Risk Management
Rank-based Unsupervised Keyword Extraction via Metavertex Aggregation
XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale
Research code for ACL 2020 paper: "Distilling Knowledge Learned in BERT for Text Generation".
Materials for ACL-2022 tutorial: Knowledge-Augmented Methods for Natural Language Processing
Data and code for EMNLP 2021 paper "FinQA: A Dataset of Numerical Reasoning over Financial Data"
This repository presents our work during a project realized in the context of the IEOR 8100 RL Class at Columbia University.
hopefully I can continuously develop the project.
https://arxiv.org/pdf/1909.04054
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
🎨 Diagram as Code for prototyping cloud system architectures
Convert natural language query to appropriate SQL, make ERPs cool again.
A monolingual and cross-lingual meta-embedding generation and evaluation framework
This is the code for ACL paper "Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network"
PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).
Several data modalities for KBs (visual, numerical, temporal, etc.)
Making large AI models cheaper, faster and more accessible
A repository used to provide an introduction to dataviz in Python
A research library for automating experiments on Deep Graph Networks
ICML'2022: NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
Lectures for INFO8010 Deep Learning, ULiège
✅ Solutions to LeetCode by Go, 100% test coverage, runtime beats 100% | LeetCode 题解