Neural Content Extraction for Poster Generation of Scientific Papers

TL;DR

This paper introduces a neural extractive model for content extraction in scientific poster generation, creating a new benchmark dataset and demonstrating effective results in extracting textual and visual elements from papers.

Contribution

It presents a novel neural extractive framework and a publicly available dataset for scientific poster content extraction, addressing previous research gaps.

Findings

The proposed model effectively extracts text, figures, and tables.

Experimental results show significant improvements over baseline methods.

The dataset and code are publicly released for future research.

Abstract

The problem of poster generation for scientific papers is under-investigated. Posters often present the most important information of papers, and the task can be considered as a special form of document summarization. Previous studies focus mainly on poster layout and panel composition, while neglecting the importance of content extraction. Besides, their datasets are not publicly available, which hinders further research. In this paper, we construct a benchmark dataset from scratch for this task. Then we propose a three-step framework to tackle this task and focus on the content extraction step in this study. To get both textual and visual elements of a poster panel, a neural extractive model is proposed to extract text, figures and tables of a paper section simultaneously. We conduct experiments on the dataset and also perform ablation study. Results demonstrate the efficacy of our proposed model. The dataset and code will be released.