I am curious as to what steps one would reasonably need to take to perform an extraction-based text summarizer.

I've taken a look at some papers I've found on Google such as this one, which explains that UPGMA is the best clustering algorithm (out of the tested set). I've also found this one to be interesting, regarding single and multi-document summarization.

I'm unclear as to whether I'd need to combine these techniques for summarization or whether it would suffice to use a tool like Gensim to model a corpus of documents and just extract the sentences with the highest vector values.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.