Explore @copenlu Open Source projects

CopeNLU (@copenlu)

copenlu

Stars
366
Global Org. Rank 28,328 (Top 10 %)
Registered over 5 years ago
Most used languages

Python
78.9 %

Jupyter Notebook
21.1 %
Location 🇩🇰 Denmark
Country Total Rank 361
Country Ranking

Jupyter Notebook
21

Python
66

xai-benchmark

A Diagnostic Study of Explainability Techniques for Text Classification

stat-nlp-book

Interactive Lecture Notes, Slides and Exercises for the DIKU NLP course, adapted from https://github.com/uclmr/stat-nlp-book

Jupyter Notebook

ALPS_2021

XAI Tutorial for the Explainable AI track in the ALPS winter school 2021

Jupyter Notebook

xformer-multi-source-domain-adaptation

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

X-MAML

Code base for " Zero-Shot Cross-Lingual Transfer with Meta Learning" papaer

check-worthiness-pu-learning

Code to reproduce the experiments for "Claim Check-Worthiness Detection as Positive Unlabelled Learning" in Findings of EMNLP 2020

scientific-exaggeration-detection

Repository for the paper "Semi-Supervised Exaggeration Detection of Health Science Press Releases" from EMNLP 2021

scientific-information-change

Code for the paper "Modeling Information Change in Science Communication with Semantically Matched Paraphrases" from EMNLP 2022

cite-worth

Data and code for the paper "CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding"

awesome-text-interpretability

A repo to keep all resources about interpretability in NLP organised and up to date

fever-adversarial-attacks

Adversarial attacks against claim detection systems at FEVER

tx-ray

Code for paper "TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP"

politihop

Jupyter Notebook

multilingual-typology-probing

Code and data for the NAACL 2022 paper "Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models".

nle_faithfulness

Repository for the paper "Faithfulness Tests for Natural Language Explanations"

intersectional-bias-pbw

dual-use

Data and code for the paper "Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing"

TESTED

This is the codebase for Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection

jensen-shannon-centroid

A lightweight package to calculate the Jensen-Shannon Centroid of a set of categorical distributions

spanex

value-probing

Data and code for the paper "Probing Pre-Trained Language Models for Cross-Cultural Differences in Values"

sufficient_facts

HumanValues

Code for the paper "Investigating Human Values in Online Communities"

Jupyter Notebook