From 187ca1884b87b95fc543af8068a7e9d038184371 Mon Sep 17 00:00:00 2001 From: nprimo Date: Thu, 14 Mar 2024 12:27:24 +0000 Subject: [PATCH] feat(nlp-scraper): fix broken link and remove optional part with broken URL --- subjects/ai/nlp-scraper/README.md | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/subjects/ai/nlp-scraper/README.md b/subjects/ai/nlp-scraper/README.md index 1e73c95bc..b7c1741fc 100644 --- a/subjects/ai/nlp-scraper/README.md +++ b/subjects/ai/nlp-scraper/README.md @@ -56,7 +56,7 @@ SpaCy](https://towardsdatascience.com/named-entity-recognition-with-nltk-and-spa The goal is to detect what the article is dealing with: Tech, Sport, Business, Entertainment or Politics. To do so, a labelled dataset is provided: [training -data](bbc_news_train.csv) and [test data](bbc_news_test.csv). From this +data](bbc_news_train.csv) and [test data](bbc_news_tests.csv). From this dataset, build a classifier that learns to detect the right topic in the article. Save the training process to a python file because the audit requires the auditor to test the model. @@ -68,11 +68,6 @@ that the model is trained correctly and not overfitted. - Learning constraints: **Score on test: > 95%** -- **Optional**: If you want to train a news' topic classifier based on a more - challenging dataset, you can use the - [following](https://www.kaggle.com/rmisra/news-category-dataset) which is - based on 200k news headlines. - #### **3. Sentiment analysis:** The goal is to detect the sentiment (positive, negative or neutral) of the news