ETDPC:一种用于电子学位论文页面分类的多模态框架
ETDPC: A Multimodality Framework for Classifying Pages in Electronic Theses and Dissertations
AI总结:
针对现有文档页面分类框架在电子学位论文(ETDs)上表现不佳的问题,本文提出带交叉注意力网络的双流多模态框架ETDPC,结合数据增强与分层分类器解决样本不平衡问题,在13类页面分类任务中全面超越最优模型。
摘要:
电子学位论文(Electronic Theses and Dissertations,简称ETDs)的提出、推广与生成已有超过25年的历史。尽管ETDs由商业或机构数字图书馆仓储托管,但它们仍是一类研究不足的学术大数据类型,部分原因是其篇幅通常长于会议论文集和期刊论文。对ETDs进行分段能让研究者研究各部分内容,读者可以导航到感兴趣的特定页面,发现并探索这些长文档中潜藏的内容。现有大多数文档页面分类框架都是为通用文档分类设计的,在ETDs上表现不佳。本文提出ETDPC框架,其主干是带有交叉注意力网络的双流多模态模型,可将ETD页面分为13个类别。为克服标注样本不平衡的挑战,我们对少数类进行了数据增强,并采用了分层分类器。ETDPC在所有类别上的表现均优于现有最优模型,13个类别中有9个的F1值达到0.84–0.96。我们还验证了其数据效率。代码和数据可在GitHub获取(https://github.com/lamps-lab/ETDMiner/tree/master/etd_segmentation)。
英文摘要:
Electronic theses and dissertations (ETDs) have been proposed, advocated, and generated for more than 25 years. Although ETDs are hosted by commercial or institutional digital library repositories, they are still an understudied type of scholarly big data, partially because they are usually longer than conference proceedings and journals. Segmenting ETDs will allow researchers to study sectional content. Readers can navigate to particular pages of interest, discover, and explore the content buried in these long documents. Most existing frameworks on document page classification are designed for classifying general documents and perform poorly on ETDs. In this paper, we propose ETDPC. Its backbone is a two-stream multimodal model with a cross-attention network to classify ETD pages into 13 categories. To overcome the challenge of imbalanced labeled samples, we augmented data for minority categories and employed a hierarchical classifier. ETDPC outperforms the state-of-the-art models in all categories, achieving an F1 of 0.84 -- 0.96 for 9 out of 13 categories. We also demonstrated its data efficiency. The code and data can be found on GitHub (https://github.com/lamps-lab/ETDMiner/tree/master/etd_segmentation).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。