Log In Sign Up

D2S: Document-to-Slide Generation Via Query-Based Text Summarization

by   Edward Sun, et al.

Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a critical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a two-step approach: 1) Use slide titles to retrieve relevant and engaging text, figures, and tables; 2) Summarize the retrieved context into bullet points with long-form question answering. Our evaluation suggests that long-form QA outperforms state-of-the-art summarization baselines on both automated ROUGE metrics and qualitative human evaluation.


Document-Level Abstractive Summarization

The task of automatic text summarization produces a concise and fluent t...

AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization

Summarization is the task of compressing source document(s) into coheren...

Just ClozE! A Fast and Simple Method for Evaluating the Factual Consistency in Abstractive Summarization

The issue of factual consistency in abstractive summarization has attrac...

Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answering

Businesses generate thousands of documents that communicate their strate...

QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications

Query-based document summarization aims to extract or generate a summary...

Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization

Long text understanding is important yet challenging in natural language...

Generating Related Work

Communicating new research ideas involves highlighting similarities and ...