davebulaval Goto Github PK

followers: 67.0 following: 128.0 repos: 40.0 gists: 4.0

Name: David Beauchemin

Type: User

Company: Baseline.québec

Bio: Ph.D. candidate in legal NLP at University Laval. Founding members of @dot-layer and @Baseline-quebec

Location: Quebec, Quebec

Blog: https://www.linkedin.com/in/david-beauchemin-918343108/

Hi there, I'm David - aka davebulaval

I’m a Ph.D. student, ML researcher, founder of an AI podcast, and an AI consultant!

I’m working on my academic research, Poutyne, Deepparse and MeaningBERT!
I’m developing my skills in NLP
I’m developing my consulting firm with colleagues: Baseline
I’m developing a bilingual AI podcast: OpenLayer
I’m developing a bilingual blog site with colleagues: .Layer

Framework I work on

Poutyne: A simplified framework for PyTorch and handles much of the boilerplating code needed to train neural networks.
Deepparse: A state-of-the-art library for parsing multinational street addresses using deep learning.
notif: A easy-to-use package to send notifications from a Python script.

Other Packages

Actuarial Symbol: Typesetting actuarial symbols easily and consistently in LaTeX.
nCopula: Construct and manipulate hierarchical Archimedean copulas with multivariate compound distributions.

Presentations I did

Articles:

📺 Latest YouTube Videos

📌 GitHub Stats

David Beauchemin's Projects

accounting

git based accounting

act_2003

Matériel de formation pour le cours de modèles linéaires en actuariat

actulab_coop

Résolution d'une problématique Actulab de Co-operators

assess_acceptability_judgments

A Python Package to Assess Acceptability Judgement using probabilistic modelling

banditsum

This repository contains python 3.7 code for the EMNLP 2018 paper "BanditSum: Extractive Summarization as a Contextual Bandit.

beamerpresenter

Simple dual screen pdf presentation software

bert_score

BERT score for text generation

blanc

Human-free quality estimation of document summaries

bonnes-pratiques-git-material

Matériel pour la formation Bonnes pratiques & Git

cookiecutter-machine-learning-research

A robust, but flexible project structure for doing and sharing machine learning research project

curriculum-vitae

This is my long, academic-style CV built with LaTex.

davebulaval

ddansddds-presentation

Detection of Duplicates Among Non-structured Data From Different Data Sources

evaluating-factuality-in-text-simplification

gestion-configuration-resultats

Gestion de la configuration et des résultats avec MLflow, Hydra et Poutyne | Configuration and results management with MLflow, Hydra and Poutyne

graal-utils

Utilitary tools

graal-website

guide_de_survie_en_actuariat

The only document you need to be an Actuary

guide_exam

Dépôt pour la mise à jour d'un guide pour les examens professionnels en actuariat.

intergenerational_equity

Repository of public information about the Intergenerational Equity project.

lens

local

W&B Local is the self hosted version of Weights & Biases

lsemap-presentation

Levraging Subword Embeddings for Multinational Address Parsing Paper Presentation https://arxiv.org/abs/2006.16152

magnitude-light

Magnitude fork that only supports Word2Vec, GloVe and fastText embeddings

ml-meetup

The code for the ML Meetup

nlp-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.