AI-Powered Summarization: Extracting Key Insights from Text, Video, and PDFs Using spaCy
In this paper we investigate the extractive summarization with spaCy for summarizing YouTube transcript, plain text and PDFs. It includes steps of text preprocessing, tokenization, named entity recognition (NER) and dependency parsing to pull in relevant data. The method we developed to extract those sentences helps keeping coherence and sense, but cut all off-topic parts. Summary is generated in an effective way for decent reading and accuracy by the system.
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-05-22
- DOI
- https://doi.org/10.5281/zenodo.15486674
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00