SlideSpawn: An Automatic Slides Generation System for Research Publications

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kumar, Keshav, Chowdary, Ravindranath
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917849551863808
author Kumar, Keshav
Chowdary, Ravindranath
author_facet Kumar, Keshav
Chowdary, Ravindranath
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17719
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SlideSpawn: An Automatic Slides Generation System for Research Publications
Kumar, Keshav
Chowdary, Ravindranath
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
H.3
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.
title SlideSpawn: An Automatic Slides Generation System for Research Publications
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
H.3
url https://arxiv.org/abs/2411.17719