Neural Content Extraction for Poster Generation of Scientific Papers
This addresses the under-investigated task of automated poster generation for scientific papers, which is incremental as it builds on document summarization but focuses on content extraction.
The authors tackled the problem of generating scientific posters by constructing a benchmark dataset and proposing a neural extractive model to simultaneously extract text, figures, and tables from paper sections, demonstrating its efficacy through experiments.
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.