Fast Prototypes for Artificial Intelligence Projects
```{raw} html
:file: profile.html
```
```{toctree}
:hidden:
nlp/index
transformers/index
better_programmer/index
algo/index
web/index
linguistique_informatique/index
high_performance_python/index
codebase/index
math/index
```
## Case studies developed for APIL Les French tech du NLP
- [1. Semi-automatic analysis of biomedical text 🇫🇷](https://www.demotal.fr/etudes-de-cas/exploiter-les-textes-biomedicaux-de-maniere-semi-automatisee/)
- [2. Better understand spell checkers to make informed decisions 🇫🇷](https://www.demotal.fr/etudes-de-cas/comprendre-pour-mieux-choisir-le-cas-des-correcteurs-orthographiques/)
- [3. Argue instead of blocking: moderating online comments while promoting debate 🇫🇷](https://www.demotal.fr/etudes-de-cas/argumenter-au-lieu-de-bloquer-moderer-des-commentaires-en-ligne-tout-en-promouvant-le-debat/)
- [4. Beyond the simple positive-negative dichotomy, discover the aspect-based sentiment analysis (ABSA) 🇫🇷](https://www.demotal.fr/etudes-de-cas/au-dela-de-la-simple-dichotomie-positif-negatif-decouvrez-lanalyse-de-sentiments-a-base-daspects/)
- [5. Extractive question answering from customer reviews 🇫🇷](https://www.demotal.fr/etudes-de-cas/extraire-des-reponses-a-des-questions-de-prospects-a-partir-des-avis-clients/)
- [6. Conducting POCs with limited data? From data quality to zero-shot learning 🇫🇷](https://www.demotal.fr/etudes-de-cas/que-faire-en-cas-de-donnees-insuffisantes-approche-centree-sur-les-donnees-et-few-shot-learning/)
## NLP and Machine Learning-related
- [1. Comparer Spacy, StanfordNLP et TreeTagger sur un corpus oral et un corpus de presse 🇫🇷](nlp/01_compara_anno_fr)
- [2. Classification de prénoms en genre 🇫🇷](nlp/02_classification_prenoms_fr)
- [3. Text Classification : TF-IDF, Word Embedding et features expertes 🇫🇷](nlp/03_classification_lemonde_fr)
- [4. How to build a spell checker with deep learning 🇬🇧](nlp/04_spell_checker_en)
- [5. Why using log scale 🇬🇧](nlp/05_log_scale_en)
- [6. How to build a LSTM-based Neural Machine Translation model with fairseq 🇬🇧](nlp/06_machine_translation_en)
- [7. Everything is translation, build a chatbot using attention and self-attention in fairseq 🇬🇧](nlp/07_chatbot_en)
## Transformers in NLP with PyTorch, TensorFlow and Hugging Face
- [1. 10 questions on Bert 🇬🇧](transformers/01_theorie_en)
- [1. 10 questions sur Bert 🇫🇷](transformers/01_theorie_fr)
- [2. Classification de commentaires avec Camembert sans prise de tête : les fondamentaux 🇫🇷](transformers/02_firstBert_fr.ipynb)
## Better Programmer
- [1. Mieux programmer en Python 🇫🇷](better_programmer/01_python_fr)
- [2. A serious guide to git 🇬🇧
](better_programmer/02_git3_en)
- [3. Understand objected-oriented programming (OOP) by building a minimal Web Scraping framework 🇬🇧](better_programmer/04_oop_web_scraping_en)
- [4. Be a responsible programmer when doing Object-Oriented Programming 🇬🇧](better_programmer/05_oop_web_scraping_cooper_en)
## Algorithms and data structures by examples in Python
- [1. Algorithm or many ways of solving a problem 🇬🇧](algo/01_intro_en)
- [1. Algorithme ou plusieurs façons de résoudre un problème 🇫🇷](algo/01_intro_fr)
- [2. Data structures or many ways of organizing your stuff 🇬🇧](algo/02_ds_en)
- [APPENDIX: Cheatsheet of algorithms and data structures 🇫🇷 🇬🇧](algo/099algo_map)
## Web Related
- [1. Complete tutorial on scraping French news from Le Monde 🇬🇧](web/01_lemonde_en)
- [1. Scraper « le monde » et construire ton propre corpus 🇫🇷](web/01_lemonde_fr.ipynb)
- [2. On your way to scraping French forums 🇬🇧](web/02_forum_en)
- [3. Deploying Django app on Ubuntu at digitalocean + SSL certificate 🇬🇧](web/03_django_en)
## Computational Linguistics in R
- [1. La loi de Zipf illustrée avec gutenbergr en R 🇫🇷
](linguistique_informatique/01_zipf_fr)
- [2. Analyse des Correspondances Multiples : le cas de l'ergatif en warlipiri 🇫🇷](linguistique_informatique/02_mca_ergatif_fr)
- [3. Analyse en composantes principales (PCA) : prépositions d’inclusion en français 🇫🇷](linguistique_informatique/03_pca_inclusion_fr)
## High performance computing
- [1. Parallelization in Python: a beginner’s guide (1, using map) 🇬🇧](high_performance_python/01_parallel_primer_en)
## Codebase
- [1. Bash](codebase/01_bash)
- [2. Tmux](codebase/02_tmux)
- [3. Python](codebase/03_python)
- [4. Pandas](codebase/06_pandas)
- [5. Pytorch](codebase/05_pytorch)
## Mathematics in Machine Learning and NLP
- [1. Machine Learning : algorithmes et mathématiques 🇫🇷](math/01_math_fr)