vansky Goto Github PK

adaptive-lm

An LM that adapts to the statistics of a test corpus to better model human performance

atomic-emacs

An atomic implementation of emacs keybindings for the Atom text editor.

azmat

A repository for our similarity stuff

bibfile_cleaner

Simple tools for bibtex bibfile organizing

c.psyd-handbook

C.Psyd Handbook

cocopro

Coherent Coreference Project

cover_letter_template

A template for generating cover letters on university letterhead

csrankings

A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

dnnseg

dtsr

A regression technique for modeling temporally diffuse effects

extended_penn_tokenizer

Fork of the Penn Treebank tokenizer

fg_acq

Filler-Gap Acquisition Package

kenlm

KenLM: Faster and Smaller Language Model Queries

lm_syneval

Code for replicating the work in "Targeted Syntactic Evaluation of Language Models." EMNLP 2018.

marcc-slurm

SLURM scripts for MARCC

mb-mapper

meg_playground

A workspace to play with MEG data

mxnet-the-straight-dope

An interactive book on deep learning. Much easy, so MXNet. Wow.

nc-tutorial

Some tutorials for using the neural-complexity toolkit

neural-complexity

A neural language model that estimates incremental processing complexity

neural-probing

Tools for probing the representations of existing neural networks

nlp-in-ling

Natural Language Processing Research in North American Linguistics Departments

nltk

NLTK Source

pltag

Psycholinguistically Motivated Tree Adjoining Grammar

ptsa

Python Time Series Analysis (PTSA, pronounced "pizza")

pylangacq

Language Acquisition Research Tools in Python

pytorch

Singularity Container for PyTorch

pytorch-pretrained-bert

The Big-&-Extending-Repository-of-Transformers: PyTorch pretrained models for Google's BERT, OpenAI GPT & GPT-2 and Google/CMU Transformer-XL.

replications

Instructions for replicating my paper results

simple_sentence_tokenizer

Tool that organizes text as one sentence per line