MilaNLP's repositories
contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021.
twitter-demographer
A python package to enrich Twitter Data
simple-generation
A python package to run inference with HuggingFace checkpoints wrapping many convenient features.
crosslingual-analysis-homotransphobia
This repository contains data and code used in the paper "A Crosslingual Analysis of Homotransphobia on Twitter" (C3NLP Workshop @ EACL23).
interpretability-mt-gender-bias
Code associated with the paper "A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation".
wordify-webapp-streamlit
New version of Wordify based on Streamlit
benchmarking-xai-misogyny
Code associated with the paper "Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection"
prompting_hate_speech
Zero-Shot Hate Speech classification using prompting. Published at the WOAH workshop (ACL 2023).
milanlp-at-mami
Code associated with the paper "MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities"
weigh-your-own-words
Code associated with the paper "Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization"
wordify-webapp
Repo for the Wordify web-app
prompting-italian-text-simplification
Code associated with the paper "Is It Really That Simple? Prompting Language Models for Automatic Text Simplification in Italian".