Coder Social home page Coder Social logo

Hi there 👋

I'm a PhD student in the Department of Linguistics at New York University. Some things I'm currently thinking about:

  • How do (large) language models generalize under distribution shift?
  • How is language model training similar to or different from human language acquisition?
  • How can we interpret language and language models through the lens of algebra?

Some things I've thought about recently:

  • Do transformer models need to be very deep to achieve good performance on compositional tasks?
  • Are there problems which transformers linear state-space models cannot solve?
  • How can the Yiddish verbal prefix צע- be analyzed as an ingressive marker?
  • Can you train a language model's tokenizer at the same time as you train the language model?

You can find a list of publications on my website. Feel free to email me ([email protected]) to ask questions about research, or reach out X @jowenpetty. If you're at NYU and want to talk in-person, email me at my NYU email.

Jackson Petty's Projects

abstract_algebra icon abstract_algebra

Abstract Algebra: An implementation of Finite Algebras: Groups, Rings, Fields, Vector Spaces, Modules, Monoids, Semigroups, and Magmas. See the ReadTheDocs link.

astr-356 icon astr-356

Homework assignments, lecture notes, and papers for ASTR 356b (Astrostatistics and Data Mining) at Yale University.

cortex-socio icon cortex-socio

Code to analyze Myke Hurley's accent as documented on episodes of the "Cortex" podcast

coursework-latex icon coursework-latex

A LaTeX3 meta-class for typesetting lecture notes, problem sets, and other academic documents.

cpsc-223 icon cpsc-223

Homework assignments, lecture notes, and papers for CPSC 223b (Data Structures and Programming Techniques) at Yale University.

earnings-call icon earnings-call

Domain-specific sentiment analysis of corporate earnings calls.

extension-zipper icon extension-zipper

A short python script to create a .zip archive of the current project state suitable for deployment to the Chrome Web Store

haskell-fp icon haskell-fp

Exercises from _Haskell Programming from First Principles_

hasse icon hasse

A web app to generate Hasse diagrams from ranking arguments

homework icon homework

A LaTeX class for typesetting homework assignments

huruf icon huruf

A simple chrome extension to make reading Arabic easier

jimart icon jimart

A LaTeX style file for Jim Wood's classes.

ktav icon ktav

A LuaLaTeX package for Hebrew transcription and transliteration

lingtex icon lingtex

A collection of LaTeX files for linguists

markdown2tex icon markdown2tex

An easy way to convert markdown into MLA-formatted LaTeX

ml-template icon ml-template

A template for developing a portable ML experimentation framework

rnn-hierarchical-biases icon rnn-hierarchical-biases

Code for "Does syntax need to grow on trees? Sources of inductive bias in sequence to sequence networks"

s4 icon s4

Structured state space sequence models

s4torch icon s4torch

PyTorch implementation of Structured State Space for Sequence Modeling (S4), based on Annotated S4.

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.