Extractive Research Slide Generation Using Windowed Labeling Ranking

TL;DR

This paper introduces an automatic slide generation method for scientific papers that uses a windowed labeling ranking approach, combining semantic and lexical features to improve extractive summarization.

Contribution

It presents a novel windowed labeling ranking algorithm for extractive summarization, outperforming existing methods like SummaRuNNer on scientific paper slide generation.

Findings

Outperforms baseline methods in ROUGE scores

Effective use of semantic and lexical features within a sentence window

Creates a scalable dataset of 5000 paper-slide pairs

Abstract

Presentation slides describing the content of scientific and technical papers are an efficient and effective way to present that work. However, manually generating presentation slides is labor intensive. We propose a method to automatically generate slides for scientific papers based on a corpus of 5000 paper-slide pairs compiled from conference proceedings websites. The sentence labeling module of our method is based on SummaRuNNer, a neural sequence model for extractive summarization. Instead of ranking sentences based on semantic similarities in the whole document, our algorithm measures importance and novelty of sentences by combining semantic and lexical features within a sentence window. Our method outperforms several baseline methods including SummaRuNNer by a significant margin in terms of ROUGE score.