Name: I-Ta Lee
Type: User
Company: Meta Platform Inc.
Bio: Research Scientist at Meta. Working on User Representation Learning for Ads Personalization. A PhD graduate from Purdue. Natural Language Processing.
Location: California, USA
Blog: https://doug919.github.io/
I-Ta Lee's Projects
Alternating Directions Dual Decomposition
http://www.ark.cs.cmu.edu/ARKref/
My favorite C programming practices.
Visualize Stanford CoreNLP's dependency trees in Stanford CoreNLP with Spacy
A LaTeX resume template, tailored for the recent graduate who aspires to be a Data Scientist/Engineer.
Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
The implementation of Entity-based Narrative Graph (ENG)
Facebook's extensions to torch/cunn.
Topic Modelling for Humans
Build a Jekyll blog in minutes, without touching the command line.
Jekyll Bootstrap theme
A content-first, sliding sidebar theme for Jekyll.
A free and open source C++ library for Discrete Approximate Inference in graphical models
Modules for analyzing LJ40K data
My implementations to fundamental machine learning models
:triangular_ruler: A flexible two-column Jekyll theme. Perfect for personal sites, blogs, and portfolios hosted on GitHub or your own server.
This repository contains code, data, and pre-trained models for the paper "Multi-Relation Script Learning for Discourse Relations"
My Website
Weakly-Supervised Modeling of Contextualized Event Embedding for Discourse Relations
Implementation of neural language models, in particular Collobert + Weston (2008) and a stochastic margin-based version of Mnih's LBL.
An Open-Source Package for Knowledge Embedding (KE)
This tool measures similarity scores between phrases.
PressureNet-SDK
Web-based data viewer for pressureNET
Server code for Android-powered barometer network