Keyword Extraction Workshop

This workshop will discuss keyword extraction, a critical Natural Language Processing (NLP) task. Search engines use keyword extraction, which is also applied in text categorization and clustering.

The workshop is divided into two parts (two Jupyter notebooks):

In the first part, using the NIPS Papers dataset as an example, we’ll explore algorithms such as:

• TF-IDF
• TextRank
• Rake
• Yake!
• And we’ll use the keyBert library.

In the second part, we’ll build a Flask web application that allows users to upload text in PDF, TXT, or DOC formats or submit it through an input form. The application will then apply keyBert to the text and return the results to the user.

Key Takeaways:

• Master key NLP concepts and keyword extraction techniques, making you proficient in analyzing and processing textual data.
• Complete a project that reinforces your learning and stands as a testament to your NLP skills.