aaronmueller

aaronmueller

aaronmueller.github.io

Aaron Mueller's personal website.

babylm.github.io

clams

Syntactic evaluation sets, attribute-varying grammars, and code for replicating the CLAMS paper. ACL 2020.

contextualized-topic-models

A python package to setup topic classification fine-tuning, run contextualized topic modeling, and run TCCTMs

emergent-syntax

Code for "How to Plant Trees in Language Models" (ACL 2023).

lm-evaluation-harness

Few-shot evaluation of language models. Fork for the BabyLM competition (CoNLL '23).

messing-with-fst

Trying out finite-state transducers.

multilingual-lm-intervention

Multilingual causal mediation analysis

syntax-icl

Code and data for In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax

aaronmueller/clams

Syntactic evaluation sets, attribute-varying grammars, and code for replicating the CLAMS paper. ACL 2020.

aaronmueller/contextualized-topic-models

A python package to setup topic classification fine-tuning, run contextualized topic modeling, and run TCCTMs

aaronmueller/emergent-syntax

Code for "How to Plant Trees in Language Models" (ACL 2023).

aaronmueller/syntax-icl

Code and data for In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax

aaronmueller/aaronmueller.github.io

Aaron Mueller's personal website.

aaronmueller/multilingual-lm-intervention

Multilingual causal mediation analysis

aaronmueller/lm-evaluation-harness

Few-shot evaluation of language models. Fork for the BabyLM competition (CoNLL '23).

aaronmueller/messing-with-fst

Trying out finite-state transducers.

aaronmueller/aaronmueller

aaronmueller/babylm.github.io

aaronmueller/dont-stop-pretraining

Adapting the Don't Stop Pretraining approach for multilingual applications. Modified by Aaron Mueller and Nathaniel Weir.

aaronmueller/dotfiles

Config files for easy setup on new UNIX-based machines

aaronmueller/earley-parser

Earley parser implementation.

aaronmueller/for-submission

aaronmueller/inverse-scaling-eval-pipeline

Basic pipeline for running different sized GPT models and plotting the results

aaronmueller/LHDFall2015

aaronmueller/mBERT-docclass

Investigation of different methods of multilingual fine-tuning for document classification with mBERT.

aaronmueller/minicons

Utility for analyzing Transformer based representations of language.

aaronmueller/mt-decoders

Basic IBM-style machine translation models with various decoding methods.

aaronmueller/neural-narrative-generation

Generating stories given prompts using GPT-2. We also try diverse decoding!

aaronmueller/nshell

nshell: a basic shell environment written in C

aaronmueller/parlai-hred

Implementation of Hierarchical Recurrent Encoder-Decoder (HRED) model for narrative generation in ParlAI.

aaronmueller/pos-hmm

Hidden Markov Model tagger

aaronmueller/smoothed-lm

Implementing smoothed n-gram language models.

aaronmueller/sparse_coding

Using sparse coding to find distributed representations used by neural networks.

aaronmueller/structural_causal_mediation

aaronmueller/tanl

aaronmueller/text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

aaronmueller/transductions

A PyTorch framework for creating, running, and reproducing experiments on seq2seq models.

aaronmueller/wiktionary-derivations-parser

For foreign editions of Wiktionary, extract derivations on each page (if they exist).