SlideSpawn: An Automatic Slides Generation System for Research Publications
This addresses the time-consuming task of creating slides for researchers, but it is incremental as it builds on existing summarization and slide generation techniques.
The authors tackled the problem of automatically generating presentation slides from research paper PDFs by developing SlideSpawn, a system that extracts structural information, predicts sentence salience using a machine learning model trained on new datasets, and selects sentences via ILP and clustering; experiments on 650 paper-slide pairs showed it generates higher-quality presentations.
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.