Summary of Presentations Are Not Always Linear! Gnn Meets Llm For Document-to-presentation Transformation with Attribution, by Himanshu Maheshwari et al.
Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution
by Himanshu Maheshwari, Sambaran Bandyopadhyay, Aparna Garimella, Anandhavelu Natarajan
First submitted to arxiv on: 21 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel graph-based solution is proposed to automatically generate presentations from long documents, addressing the challenges of non-linear narrative and faithful content representation. The approach learns a graph from the input document and combines it with a graph neural network and a language model (LLM) to produce a presentation with slide-level attribution. Experimental results demonstrate the merit of this method compared to directly using LLMs for this task. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops an innovative way to create presentations from long documents, which requires a more engaging and non-linear narrative than just summarizing the content. The proposed approach uses graphs and special types of neural networks called graph neural networks (GNNs) and language models (LLMs). This method can generate presentations with accurate information about where each piece of text comes from in the original document. |
Keywords
» Artificial intelligence » Graph neural network » Language model
