SlideSpawn: An Automatic Slides Generation System for Research Publications

TL;DR

SlideSpawn is an automated system that converts research PDFs into concise, structured presentation slides by analyzing document structure, predicting salient sentences, clustering content, and incorporating relevant graphics.

Contribution

The paper introduces SlideSpawn, a novel system that automatically generates research presentation slides from PDFs using machine learning and optimization techniques, including new datasets.

Findings

Generated slides are of higher quality than baseline methods.

The system effectively identifies salient content for slides.

Incorporates visual elements to enhance presentation clarity.

Abstract

Research papers are well structured documents. They have text, figures, equations, tables etc., to covey their ideas and findings. They are divided into sections like Introduction, Model, Experiments etc., which deal with different aspects of research. Characteristics like these set research papers apart from ordinary documents and allows us to significantly improve their summarization. In this paper, we propose a novel system, SlideSpwan, that takes PDF of a research document as an input and generates a quality presentation providing it's summary in a visual and concise fashion. The system first converts the PDF of the paper to an XML document that has the structural information about various elements. Then a machine learning model, trained on PS5K dataset and Aminer 9.5K Insights dataset (that we introduce), is used to predict salience of each sentence in the paper. Sentences for slides are selected using ILP and clustered based on their similarity with each cluster being given a suitable title. Finally a slide is generated by placing any graphical element referenced in the selected sentences next to them. Experiments on a test set of 650 pairs of papers and slides demonstrate that our system generates presentations with better quality.