mirandrom

HipoRank

(EACL 2021) Discourse-Aware Unsupervised Summarization of Long Scientific Documents

PyS2

A python library for the Semantic Scholar (S2) API with typed pydantic objects and various nifty functionalities.

py-bpe

Pure python implementation of byte pair encoding (subword tokenization)

CrisisTweetMap

(Covid-19 EMNLP 2020) Real-time Classification, Geolocation and Interactive Visualization of COVID-19 Information Shared on Social Media to Better Understand Global Developments

zsl

Zero-sum learning (ACL 2025)

arxiv-net

Improved content navigation for arXiv

am-i-the-asshole

Machine learning to tell you whether you are an asshole or not

balaur

(Findings of EMNLP 2023) Balaur: Language Model Pretraining with Lexical Semantic Relations

mcgill-nlp.github.io

mila-docs

Mila technical documentation

mirandrom.github.io

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

ordered-rouge

An extension of ROUGE-1.5.5 which takes information ordering into account.

living-review-mockup

rouge

Pure python implementation of ROUGE, designed for extendability and use in an RL setting

xl-heatmap

Extra-large embedding similarity heatmaps with plotly dash