Personal website

Take Home Test - Investigating Diagnostic and Causal Probing

Code to run experiments of paper "How to Compute the Probability of a Word"

This code is used to generate random text using First-come First-serve Monkeys.

Code to compute a word's probability using the fixes from "How to Compute the Probability of a Word"

This repository accompanies the paper "Revisiting the Optimality of Work Lengths"

Code to train language models using fairseq.

Code to download and tokenize wikipedia data.

Code to use Neighbor Based Node Embeddings (NBNE) method to create representations to nodes in a graph.

Code for "Meaning to Form: Measuring Systematicity as Information"

Create a map from wordform to part-of-speech using UD data

Code to get embeddings from wikipedia with BERT

This code accompanies the paper "Disambiguatory signals are stronger in word initial positions" published in EACL 2021.

Code to train a dependency parser model

Studying phonotactics and how it relates to other language features