FigSum: Automatically Generating Structured Text Summaries for Figures in Biomedical Literature

Figures are frequently used in biomedical articles to support research findings; however, they are often difficult to comprehend based on their legends alone and information from the full-text articles is required to fully understand them. Previously, we found that the information associated with a single figure is distributed throughout the full-text article the figure appears in. Here, we develop and evaluate a figure summarization system - FigSum, which aggregates this scattered information to improve figure comprehension. For each figure in an article, FigSum generates a structured text summary comprising one sentence from each of the four rhetorical categories - Introduction, Methods, Results and Discussion (IMRaD). The IMRaD category of sentences is predicted by an automated machine learning classifier. Our evaluation shows that FigSum captures 53% of the sentences in the gold standard summaries annotated by biomedical scientists and achieves an average ROUGE-1 score of 0.70, which is higher than a baseline system.