Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution
Preprint
Abstract
Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can come from different and non-contiguous parts of the given document. However, it is difficult to incorporate such non-linear mapping of content to slides and ensure that the content is faithful to the document. LLMs are prone to hallucination and their performance degrades with the length of the input document. Towards this, we propose a novel graph based solution where we learn a graph from the input document and use a combination of graph neural network and LLM to generate a presentation with attribution of content for each slide. We conduct thorough experiments to show the merit of our approach compared to directly using LLMs for this task.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- D2S: Document-to-Slide Generation Via Query-Based Text Summarization2021
- On Learning Text Style Transfer with Direct Rewards2021
- VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles2020
- Automatically Generating Engaging Presentation Slide Decks2019
- MSMO: Multimodal Summarization with Multimodal Output2018
- Presentation slides generation from scientific papers using support vector regression2017
- Phrase-Based Presentation Slides Generation for Academic PapersProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Automatic era: Presentation slides from Academic paper2016
- ‘Auto-Presentation’: A Multi-Agent System for Building Automatic Multi-Modal Presentation of a Topic from World Wide Web Information2006