aryamanarora

causalgym

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

schwa-deletion

Code for the ACL 2020 Paper on Schwa Deletion in Hindi and Punjabi

india-census-2011

D3.js visualization of the language parts of the 2011 Census of India.

bhasacitra

Map of South Asian language resources, and areal features.

nano-causal-interventions

Extremely simple implementation of path patching (aka causal scrubbing) in PyTorch.

induction

Induction heads

carmls-hi

Hindi SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al., 2018) annotation scheme and guidelines.

diabetes-predictor

A diabetes predictor website that uses the UCI Pima Indians Diabetes Database and some machine learning.

aryamanarora.github.io

Personal website, in raw HTML + CSS

fbla

FBLA Coding and Programming

urdu-metre

Tool for automatically doing scansion of Urdu poetry.

creoles

Project website for LING 251

docs

Universal Dependencies online documentation

Easy-Transformer

entropy-estimation

gpt2-interpret

Utilities that replicate past mechanistic interpretability work on GPT-2

grambank

grammaticalisation

Visualisation from the World Lexicon of Grammaticalization.

LLM-Adapters

clone of LLM-Adapters

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

llm-zoo

Catalogue of large language models and useful information about them.

mamba-chat

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

nlp-in-ling

Natural Language Processing Research in North American Linguistics Departments

pyvene

A Library for Aligning Causal Variables with Transformers Model

rycolab.github.io

san

snacs

Finetuning models on SNACS corpora.

south_asia_lexical_strata

travel-map

wug-gender

Predicting grammatical gender of wug words with neural sequence models.