Add OCR with w2v tutorial

Living-with-machines / DeezyMatch

A Flexible Deep Learning Approach to Fuzzy String Matching

https://living-with-machines.github.io/DeezyMatch/

Other

134 stars 34 forks source link

Add OCR with w2v tutorial #126

Closed mcollardanuy closed 2 years ago

review-notebook-app[bot] commented 2 years ago

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

mcollardanuy commented 2 years ago

Hi @fedenanni @kasra-hosseini could you have a look at the OCR tutorial? The order is (1) prepare_dataset.ipynb and (2) tutorial_ocr_w2v.ipynb. Thanks!

kasra-hosseini commented 2 years ago

In prepare_dataset.ipynb, we are missing the images:

images/ocr_aligment.png
images/cmp_machineNN.png

and:

Source: [HERE THE SOURCE]

kasra-hosseini commented 2 years ago

In prepare_dataset.ipynb, it is said "a word's context is its meaning". Should we change this to

"words that are used and occur in the same contexts tend to purport similar meanings (see distributional semantics)."

mcollardanuy commented 2 years ago

Images added!

kasra-hosseini commented 2 years ago

I close this PR as we moved all the notebooks to a new repo: DeezyMatch_tutorials (private for now, soon to be public)