Suggestions about how to apply Named Entity Recognition or Related

Beginners
1

I am doing web scraping on an e-commerce site and have access to the descriptions of houses, which are provided in paragraphs of text (in Spanish).

I need a model that can extract useful information from these texts, such as the number of rooms in the house or whether it has a pool (if so, I would append a 1 to my Python list).

I do not know if this is for Named Entity Recognition (NER) or applying Question Answering (QA), if positive responses, then add information to my list of Python.

The outcome would be a more comprehensive dataset, using NLP to analyze the features the house offers.

Do you have any suggestions for a model that could do this?

The vocabulary must be related to real estate and in Spanish.

2

hi @leonelmorenoa
Question answering sounds reasonable. You might try this one, it can work better than a generic model: GAIR/rst-information-extraction-11b · Hugging Face

Please check

and
GitHub - 1rgs/jsonformer: A Bulletproof Way to Generate Structured JSON from Language Models as well.

1 Like
3

Thank you so much @mahmutc

4

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.