Terence Eden1d ago

I think I have a genuine need for an #LLM. Can someone tell me if this is possible?

@openbenches contains ~40k text inscriptions.

Someone wants to know how many are dedicated to men, how many to women.

"To Grandma Sylvia" is obvious.
"To R Smith" is not.

Could an AI give a rough estimate of the gender of a subject?

Could it ignore text relating to who the inscription is from? "To Granny from Dave and Alice".

What would be the most accurate / cheapest / fastest / easiest tool to work with?

Show threadGiles1d ago
@Edent @openbenches Oh. This is tickling something in the brain pan about trying to determine if a company name is a sole trader or not from a couple of years ago. IIRC I tried to do it with plain old NLTK, which incorporated tokenising and tagging part of speech, including proper name extraction. That might get you so far. Then other techniques for guesstimating gender. I’ll see if the code is in anyway useable! In fact I’ll first see if I can find the code…
Show threadGiles
@Edent @openbenches Haven’t found my code, but pretty sure this was the sort of code I was using… https://www.geeksforgeeks.org/nlp/nlp-extracting-named-entities/
NLP | Extracting Named Entities - GeeksforGeeks

Your All-in-One Learning Portal: GeeksforGeeks is a comprehensive educational platform that empowers learners across domains-spanning computer science and programming, school education, upskilling, commerce, software tools, competitive exams, and more.

GeeksforGeeks
Mar 24 at 8:50pmWeb
Show threadDavid Kane1d ago

@gilesdring @Edent I did something similar with the charity register a while ago: https://dkane.net/2018/names-shared-by-genders/

The list of charity trustees has (or used to at least) some instances with an unambiguous title which I used to extract a list of names .

Names shared by genders

David Kane