Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models

Abstract

In this paper, we revisit the challenging problem of unsupervised single-document summarization and study the following aspects, (i) Integer linear programming (ILP) based algorithms, (ii) Parameterized normalization of term and sentence scores, and (iii) Title-driven approaches for summarization. We describe a new framework, NewsSumm, that includes many existing and new approaches for summarization including ILP and title-driven approaches. NewsSumm’s f lexibility allows to combine different algorithms and sentence scoring schemes seamlessly. Our results combining sentence scoring with ILP and normalization are in contrast to previous work on this topic, showing the importance of a broader search for optimal parameters. We also show that the new title-driven reduction idea leads to improvement in performance for both unsupervised and supervised approaches considered.

Avisha Das

Research Fellow

My research interests include natural language understanding and generation with a focus on Biomedical NLP and AI Security.