|
I'm currently researching the available algorithms for document summarization and query-biased and query-focused snippet extraction and ranking. I found a few ML-based algorithms but I'm specifically looking to build a very simple, general-purpose algorithm that does not maintain state and analyzes a plain-text, unformatted document. Does anyone know where I could find some introductory material on the subject? |
I'm interested in this question too. What ML-based approaches have you seen?