Git Product home page Git Product logo

Brian Lester

About Me

Welcome to my github. I am very into machine learning and specifically natural language processing.

Publications

If you’re interested on my work in NLP research, checkout my work on Google Scholar or Semantic Scholar.

My software

In my opinion a lot of current research skates over details and many small bug creep into the work. At worse this can change results and at best it means what you implemented is not what you actually described. A common source of these errors in NLP research is padding, you can see the slides of a talk I have about it here.

In the interest of fixing these sorts of problem, and my general belief in open source software, I have a collection of small, (hopefully) well-engineered, tools that will help facilitate reuse where these sorts of error have already been accounted for.

Links

Brian Lester's Projects

arcs-py icon arcs-py

Arc-Eager and Arc-Hybrid Greedy Dependency Parser with Dynamic Oracle in Python (with no Dependencies!)

baseline icon baseline

Strong Deep-Learning Baseline algorithms for NLP

beamer-image icon beamer-image

A docker image that has all the things I normally use to create BeamerSlides with

bert icon bert

TensorFlow code and pre-trained models for BERT

crossweigh icon crossweigh

CrossWeigh: Training Named Entity Tagger from Imperfect Annotations

cs_1622_compilers icon cs_1622_compilers

Pieces of a compiler for the MINI-Java language for CS 1622 at The University of Pittsburgh

cs_1645 icon cs_1645

Introduction to High Performance Computing at the University of Pittsburgh

cs_1652_project_1 icon cs_1652_project_1

The first Project for CS 1652 Computer Networking using standard Unix Sockets

delta-of-delta icon delta-of-delta

A simple python library demonstrating some time series encoding schemes.

dynet icon dynet

DyNet: The Dynamic Neural Network Toolkit

file-or-name icon file-or-name

Python Library to transparently handle arguments that are file paths or file objects.

fizzbuzz icon fizzbuzz

A fizzbuzz implementation without double checking.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.