Pathology Dynamics at BioLaySumm: the trade-off between Readability, Relevance, and Factuality in Lay Summarization
Pathology Dynamics at BioLaySumm: the trade-off between Readability, Relevance, and Factuality in Lay Summarization
复制标题
DOI：
10.18653/v1/2023.bionlp-1.63
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Irfan Al-Hussaini;Austin Wu;Cassie S. Mitchell
中科院分区：
文献类型：
--
作者：
Irfan Al-Hussaini;Austin Wu;Cassie S. Mitchell
通俗摘要旨在为非专业观众简化复杂的科学信息。本文研究了在生物医学长文摘要中可读性和相关性之间的权衡。我们引入了一个两阶段框架，在BioLaySumm 2023的第一个子任务中获得了最佳的可读性指标，FleschKincaid等级为8.924，DaleChall可读性得分为9.188。然而，这是以降低相关性和真实性为代价的，强调了在通俗摘要中平衡可读性和内容保留的固有挑战。第一阶段使用大型语言模型生成摘要，例如具有LSG注意力的BART。第二阶段采用零镜头句子简化方法，以提高摘要的可读性。在第二子任务中，采用混合数据集来训练能够生成层摘要和摘要的模型。这种方法实现了最好的可读性得分，并与其他领先的方法共享最高的整体排名。我们的研究强调了开发有效方法的重要性，这些方法可以在保持信息完整性的同时创建可访问的非专业摘要。未来的工作将在一个联合优化框架内整合简化和摘要生成，该框架将生成高质量的非专业摘要，有效地将科学内容传达给更广泛的受众。
Lay summarization aims to simplify complex scientific information for non-expert audiences. This paper investigates the trade-off between readability and relevance in the lay summarization of long biomedical documents. We introduce a two-stage framework that attains the best readability metrics in the first subtask of BioLaySumm 2023, with 8.924 FleschKincaid Grade Level and 9.188 DaleChall Readability Score. However, this comes at the cost of reduced relevance and factuality, emphasizing the inherent challenges of balancing readability and content preservation in lay summarization. The first stage generates summaries using a large language model, such as BART with LSG attention. The second stage uses a zero-shot sentence simplification method to improve the readability of the summaries. In the second subtask, a hybrid dataset is employed to train a model capable of generating both lay summaries and abstracts. This approach achieves the best readability score and shares the top overall rank with other leading methods. Our study underscores the importance of developing effective methods for creating accessible lay summaries while maintaining information integrity. Future work will integrate simplification and summary generation within a joint optimization framework that generates high-quality lay summaries that effectively communicate scientific content to a broader audience.