English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present an approach for adapting convolutional neural networks for objectrecognition and classification to scientific literature layout detection(SLLD), a shared subtask of several information extraction problems. Scientificpublications contain multiple types of information sought by researchers invarious disciplines, organized into an abstract, bibliography, and sectionsdocumenting related work, experimental methods, and results; however, there isno effective way to extract this information due to their diverse layout. Inthis paper, we present a novel approach to developing an end-to-end learningframework to segment and classify major regions of a scientific document. Weconsider scientific document layout analysis as an object detection task overdigital images, without any additional text features that need to be added intothe network during the training process. Our technical objective is toimplement transfer learning via fine-tuning of pre-trained networks and therebydemonstrate that this deep learning architecture is suitable for tasks thatlack very large document corpora for training ab initio. As part of theexperimental test bed for empirical evaluation of this approach, we created amerged multi-corpus data set for scientific publication layout detection tasks.Our results show good improvement with fine-tuning of a pre-trained basenetwork using this merged data set, compared to the baseline convolutionalneural network architecture.

Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks