Interactive summarization is a task that facilitates user-guided exploration of information within a document set.
Keyphrase extraction has been extensively researched within the single-document setting, with an abundance of methods, datasets and applications.
In this paper, we develop an end-to-end evaluation framework for interactive summarization, focusing on expansion-based interaction, which considers the accumulating information along a user session.
Allowing users to interact with multi-document summarizers is a promising direction towards improving and customizing summary results.
Conducting a manual evaluation is considered an essential part of summary evaluation methodology.
We present a novel interactive summarization system that is based on abstractive summarization, derived from a recent consolidated knowledge representation for multiple texts.