BayesForDays

elc-bert

yoyodyne

Small-vocabulary sequence-to-sequence generation with optional feature conditioning

framework

A static site generator for data apps, dashboards, reports, and more. Observable Framework combines JavaScript on the front-end for interactive graphics with any language on the back-end for data analysis.

openlexicon

Access to lexical databases

stat_rethinking_2024

gmm-torch

Gaussian mixture models in PyTorch.

hopsparser

A neural dependency parser that does its best

noun-compound-interpretation

UBC Summer 2022 Undergraduate Research Project

intergroupEntropy

Measuring entropy in communication between and within groups

jsPsych

Create behavioral experiments in a browser using JavaScript

GPT2ForwardBackward

Code for running forward and backward versions of GPT2

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

dockerize

Utility to simplify running applications in docker containers

wordnet-homonymy

Openreview

data from ICLR OpenReview and code for data analysis

TransformerDemo

Pytorch nn.Transformer Demo

zeugma_norms

Relatedness norms of ambiguous words using zeugmatic sentences.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

prompt_semantics

This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”

AusterweilLab.github.io

Lab Website. site files copied to wisc.edu

Phrase-Detectives-Corpus-2.1.4

Phrase Detectives Corpus 2.1.4

Polyseme-Word-Sense-Similarity-Dataset-v1

This is the first version of a Polyseme Word Sense Similarity Dataset collected by Janosch Haber and Massimo Poesio for the DALI Project at queen Mary University of London.

UniversalAnaphora

An initiative to collect and distribute resources for co-reference resolution in a unified standard.

devU-api

Auto-grading 4.0 API

Mask-Language-Model

pytorch； mask language model ； bert

rstWeb

Repository for rstWeb, a browser based annotation interface for Rhetorical Structure Theory

gum

Repository for the Georgetown University Multilayer Corpus (GUM)

mucoco

Official Code for the papers: "Controlled Text Generation as Continuous Optimization with Multiple Constraints" and "Gradient-based Constrained Sampling from LMs"

github-typo-corpus

GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors

pynlpl

PyNLPl, pronounced as 'pineapple', is a Python library for Natural Language Processing. It contains various modules useful for common, and less common, NLP tasks. PyNLPl can be used for basic tasks such as the extraction of n-grams and frequency lists, and to build simple language model. There are also more complex data types and algorithms. Moreover, there are parsers for file formats common in NLP (e.g. FoLiA/Giza/Moses/ARPA/Timbl/CQL). There are also clients to interface with various NLP specific servers. PyNLPl most notably features a very extensive library for working with FoLiA XML (Format for Linguistic Annotation).