Context: I want to determine if someone's written review contains content that is relevant to a paragraph that they are reviewing.
To do so, I am trying to determine if one paragraph is relevant to another paragraph. I initially tried to use TF-IDF to calculate the relevancy, but I think TF-IDF works well for determining if one paragraph is relevant to a whole set of paragraphs. I only want to determine if two paragraphs are relevant with each other.
What would be a good approach for this problem?