https:\/\/flaven.fr\/2021\/03\/improve-a-cmss-photos-library-qualification-with-ai-object-detection-from-images-in-python-with-opencv-and-yolo\/<\/a><\/li>\n
https:\/\/flaven.fr\/2020\/09\/quick-overview-about-using-nlp-for-a-cms-customer-support-faqs-turn-to-a-chatbot-or-cms-editorial-features-for-journalist-keywords-extraction-using-spacy-rake-tensorflow-pytorch\/<\/a><\/li>\n<\/ul>\n
For this post, you can find all files for each project on my GitHub account. See https:\/\/github.com\/bflaven\/ia_usages\/tree\/main\/ml_label_studio<\/a><\/b> This action often allows both to deepen understanding and practicing. At the same time, you should not hesitate to throw away a technology or a tool if it proves to be too time-consuming for a poor result!<\/b><\/p>\n I have focus my attention on a very basic question: How to build a custom NER with the help of Spacy? This question leads me to a bigger one: In NLP, how to build a machine learning pipeline with Label Studio or Docanno (open source), instead of Prodigy (paid)?<\/p>\n Choosing the right tool answered to the thorny question of ensuring data quality and might give some accuracy to your model! Otherwise, you may fall in “Shit in, Shit out” curse. <\/p>\n Like always, to ensure quality and accuracy, you must get down to the nitty-gritty. So, if you can, you must look under the hood and get our hands dirty with code.<\/p>\n The importance of the Labeling process or annotating inside the ML pipeline.<\/b> Source: https:\/\/www.researchgate.net\/figure\/A-common-pipeline-for-annotating-data-and-building-models-with-machine-learning_fig1_359227212<\/a><\/p>\n So, for the sake of simplicity, the labeling process can be even cut into 6 steps<\/p>\n “Simplest” Labeling Process with 6 Steps<\/b> Here is a quick terminology to grasp roughly the essential of the Labeling process.<\/b><\/p>\n Source: https:\/\/www.youtube.com\/watch?v=VBnhpMLpBB0<\/a><\/p>\n Like as I said before discovering the labelling process, my original question was to create a specific NER with the help of Spacy.<\/p>\n Indeed, the ability to recognize name entities is paramount but most of the time you may need a specific NER because you are working with domain specific data e.g. Finance, Medicine, Cooking, History, Biology, African Football, Law, Cinema, Television, Transport… Anyway, there are many domains where you have to deal with specific words that which sounds like gibberish to laymen!<\/p>\n I have to talk a little bit about methodology. First of all, use cases have always help me to enliven my learning process. So, I sure look after explanations but also select use cases, mostly quick and reproducible. Even if, use cases must be counterbalanced by the consciousness that mere imitation is not sufficient to fully understand AI\/ML! Reproducing a tutorial will never turn you into a specialist. Thanks God, become a specialist is not my objective. As much as possible, I try to isolate real process like the labeling one to master IA cases and minimizing uncertainty when working on Projects in Real Life.<\/p>\n In the field of NLP, create a “custom NER” is a classic example. This is most often favored example. Indeed, it is the most intuitive process with the most striking results, a bit like writing your first test under Cypress on you website homepage, creating a blog in 20 min on RoR or finally building your WP plugin in 5 minutes.<\/p>\n For any POC to have value, meaning instructive and profitable, two things are needed:<\/p>\n So, here is a list of my objectives in term of learning value:<\/p>\n Just as quick reminder, as I have read earlier some elements on Lean. I found interesting to mix also this investigation on my labeling process exploration with some rules from Lean methodology. All these principles are so many reminders when you get lost in explanations or in useless code creation.<\/b><\/p>\n Gemba is the equivalent of the crime scene in Japanese.Remain on the ground where you create and produce value. In business, Genba refers to the place where value is created;<\/b>Source: https:\/\/en.wikipedia.org\/wiki\/Gemba<\/p>\n The Plan-Do-Check-Act avoids investing on false leads. Lean favors countermeasures that are ingenious, economical and whose effect can be verified quickly. I can resist to quote these “waste hole” examples as I definitely fell once in while in one of those traps.<\/p>\n Type of waste: the 7 examples of waste<\/i><\/p>\n So, the purpose is either to flesh out and make alive a real procedure, process or pipeline for annotating data and building models with machine learning for any kind of content.<\/p>\n In most of the case, I have replaced Prodigy by Label Studio or even Doccano. I would rather go for Label Studio as it is compatible with DAGSHub. Label Studio gave a great documentation and many examples for any kind of annotation process including sounds, images, videos….<\/p>\n Some explanations can be found in the readme on https:\/\/github.com\/bflaven\/BlogArticlesExamples\/tree\/master\/ml_label_studio<\/a><\/p>\n #1 Machine Learning for NLP: Labeling process to train a “custom” NER for Spacy with Label Studio
\nBut what if I want to go further than the simple use? Like in any learning process, to become a “doer” requires an essential step: selecting tools.<\/b><\/p>\n
\n![](\"https:\/\/flaven.fr\/wp-content\/uploads\/2023\/08\/A-common-pipeline-for-annotating-data-and-building-models-with-machine-learning.png\")
<\/p>\n\n
\n![](\"https:\/\/flaven.fr\/wp-content\/uploads\/2023\/08\/labeling_process_small.png\")
<\/p>\n\n
Methodology<\/h1>\n
The Custom NER example<\/h2>\n
\n
Always define objectives<\/h2>\n
\n
Remember few LEAN AGILE principles and make some mix<\/h2>\n
\n
\n
Set the environments with anaconda<\/h2>\n
\r\n# list the envs\r\nconda info --envs\r\n\r\n# ml_with_label_studio\r\nsource activate ml_with_label_studio\r\npip freeze > requirements_ml_with_label_studio.txt\r\nconda deactivate\r\n\r\n# tagging_entity_extraction\r\nsource activate tagging_entity_extraction\r\npip freeze > requirements_tagging_entity_extraction.txt\r\nconda deactivate\r\n\r\n\r\n# Create a anaconda environment named tagging_entity_extraction\r\nconda create --name tagging_entity_extraction python=3.9.13\r\nconda info --envs\r\nsource activate tagging_entity_extraction\r\nconda deactivate\r\n\r\n# if needed to remove an environment\r\nconda env remove -n [NAME_OF_THE_CONDA_ENVIRONMENT]\r\nconda env remove -n chainlit_python\r\nconda env remove -n ai_chatgpt_prompts\r\n\r\n# update conda \r\nconda update -n base -c defaults conda\r\n\r\n# to export requirements\r\npip freeze > requirements_ml_with_label_studio.txt\r\npip freeze > requirements_tagging_entity_extraction.txt\r\n\r\n# to install\r\npip install -r requirements_ml_with_label_studio.txt\r\npip install -r requirements_tagging_entity_extraction.txt\r\n\r\n<\/pre>\n
Use cases<\/h2>\n
Videos to tackle this post<\/h2>\n
\n