Tutorial 2: Extracting Information from Documents

[@mdrasel-gh5yf]

Andrew Halterman's Notebook walkdown was great! Very clear and intuitive explanations.

[@Pingu_astrocat21]

Thank you for this :) very informative also cat at 21:17

[@lencazero4712]

Great video. I wish I could have disabled the human faces on the right and focus on the lecture :(.

[@msnbmnt]

Andrew! I know I'm a bit late here but wild to hear your voice, man. Working on some similar things these days. Hope you're doing well.

[@avi0gaur]

Crisp and clear, well done!

[@mehrdadhosseini3278]

Hello, thanks for well explanation. I have a question. How can we extract location and group of topic together?, my mean is in a review, we can extraction locations and the related verbs in that location simultaneously.

[@chijiean6316]

Hi! How can we have access to the jupyter notebook from the video?

[@duetplay4551]

Wondering how the last "clean_prase( )" function works. Any one can provide a subtree for me to try? thx

[@ayushabhinav7627]

If the file from which the information is to be extracted is in pdf form how to extract data from it ?

[@mansamusa559]

read the pdf file, f.e. with python PyPDF2 and extract it.. If its an image in the pdf, you need to apply ocr otherwise you can directly read its content.

[@michaeldebellis4202]

Click on the “more” link in the video description. There is a link to the code and other supporting information

[@Julia-ej4jz]

Very nice, thank you!

[@kritikajain5417]

How can we extract information from documents like invoices ? For example invoice number , name , sender , address subtotal etc.

[@thomastudu2977]

A custom program written in any language , which includes text position based classification will do just fine.

[@Dr.GyanPrakash-u9y]

great work

[@elkadriwadii9152]

Great work !

[@elkadriwadii9152]

I have a problem when executing this cell code : import jsonlines from tqdm.autonotebook import tqdm import jsonlines import re import spacy from spacy import displacy assert spacy.__version__ == "3.1.3" ****************************** and i get this message error : AssertionError Traceback (most recent call last) in 7 import spacy 8 from spacy import displacy ----> 9 assert spacy.__version__ == "3.1.3" *********** can you help me to fix error please?

[@curiousronak]

Remove or comment this line simple 😄

[@yunianitarahmawati9069]

me too... i have error in that line code..