Two ways of text summarization: extractive and abstractive. In extractive text summarization we extract important tokens as sentences from the text and arrange them together, whereas in abstractive we generate a summary that keeps original intent in our own language . But here we have worked upon four extractive based algorithms.
When a model gives completely different output text as compared to original text or we can say that it produces a new sentence to get the summary.
When model extracts valuable tokens/phrases and sentences as output from the original text.Four algorithms we have implemented till now both use extractive methodologies. The algorithms we have covered in the project are NLTK, spaCy, Sumy and Gensim.
NLTK stands for natural languages toolkit. Programs for symbolic and statistical natural Language Processing Lexical analysis: Word and Text Tokenizer N-gram and Collocation Part of speech tagger Named entity recognition.
spaCy used in NLP projects acts as a one-stop-shop for various tasks, example Tokenization, (POS) tagging.
Sumy is able to create extractive summary. That means it tries to find the most significant sentences in the document(s) and compose it into the shortened text.
This module automatically summarizes the given text, by extracting one or more important sentences from the text. In a similar way, it can also extract keywords.
Provide the URL of the video for which you want the summarized text.
Select the Algorithm that you want to use in Summarizer. If you don't have knowledge about algorithms you can select default(spaCy) for ost efficient results :)
Provide the length percentage of summary to the content text.
Click on Summarize button.
If you want to download the file you can click on Download button.