jarobyte91

pytorch_beam_search

A simple library that implements search algorithms for sequence models written in PyTorch.

post_ocr_correction

Source code for the paper "Post-OCR Document Correction with Large Ensembles of Character Sequence-to-Sequence Models"

quotes

Source code for the paper "QuOTeS: Query-Oriented Technical Summarization"

auto_summ

Online demo of the paper "Unsupervised Document Summarization using pre-Trained Sentence Embeddings and Graph Centrality" published in the Second Scholarly Document Processing Workshop at NAACL-HLT 2021.

dcsi_2022

Source code for the paper "ChunkSumm: Extending BERT for Long Document Summarization"

detests_2022

Source code for the paper "MALNIS at IberLEF-2022 DETESTS Task: A Multi-Task Learning Approach for Low-Resource Detection of Racial Stereotypes in Spanish"

analisis_numerico

Este repositorio incluye varias rutinas de análisis numérico escritas en python 3.5

bert_embeddings

CLI tool to extract embeddings using BERT

control_de_autoridades

jupyter_presentations

This repository shows some useful tips about how to tweak the plots and images of Jupyter notebooks and reveal.js slides.

malnis_data

Source code for the paper "MALNIS-DATA: Automatically Building Datasets for Scientific Query-Focused Summarization and Citation Prediction"

elektra_captacion

Análisis Exploratorio de Captación en Crystal Data

flavia_words

Graph-WaveNet

graph wavenet

gym

A toolkit for developing and comparing reinforcement learning algorithms.

humor

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

jarobyte91

personal readme

manual

This manual describes the methodology to clean databases found in datos.gob.mx

nserc_labelling

A simple Flask server to explore document collections

quotes_gt

QuOTeS Ground Truth collector

science-parse

Science Parse parses scientific papers (in PDF form) and returns them in structured form.

setup