Code for our ACL '23 paper titled "Grokking of Hierarchical Structure in Vanilla Transformers"

Fast, general, and tested differentiable structured prediction in PyTorch

Heuristic Analysis for NLI Systems

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Massively multilingual pronunciation mining

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Simple creation of data classes from dictionaries.

Define commands which run reformatters on the current Emacs buffer

A formatter for Python files

org-mode modules for citations, cross-references, bibliographies in org-mode and useful bibtex tools to go with it.

Browse and import bibliographic references from CrossRef, DBLP, HAL, arXiv, Dissemin, and doi.org from Emacs

The Standard Ebooks toolset for producing our ebook files.

Code and pre-trained model for: Deep Semantic Role Labeling: What Works and What's Next

A TensorFlow implementation of DeepMind's WaveNet paper

A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Extension of the mate-tools NLP pipeline

Linear algebra in TypeScript.

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

The official released annotations, both in .prop pointer format and as conll files. Does not contain the source texts

Monokai for Emacs is a port of the popular TextMate theme Monokai by Wimer Hazenberg.

An Open Source Machine Learning Framework for Everyone

Deep learning with dynamic computation graphs in TensorFlow

A general-purpose encoder-decoder framework for Tensorflow

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.