Extractive vs. NLG-based Abstractive Summarization of Evaluative Text: The Effect of Corpus Controversiality

Extractive summarization is the strategy of concatenating extracts taken from a corpus into a summary, while abstractive summarization involves paraphrasing the corpus using novel sentences. We define a novel measure of corpus controversiality of opinions contained in evaluative text, and report the results of a user study comparing extractive and NLG-based abstractive summarization at different levels of controversiality. While the abstractive summarizer performs better overall, the results suggest that the margin by which abstraction outperforms extraction is greater when controversiality is high, providing aion outperforms extraction is greater when controversiality is high, providing a context in which the need for generationbased methods is especially great.