Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks
This addresses the challenge of information extraction for researchers across disciplines by enabling automated segmentation of scientific documents, though it is incremental as it builds on existing deep learning methods.
The paper tackles the problem of extracting structured information from scientific publications by developing an end-to-end learning framework for layout detection, treating it as an object detection task on digital images without text features, and shows good improvement through fine-tuning a pre-trained network on a merged dataset compared to a baseline.
We present an approach for adapting convolutional neural networks for object recognition and classification to scientific literature layout detection (SLLD), a shared subtask of several information extraction problems. Scientific publications contain multiple types of information sought by researchers in various disciplines, organized into an abstract, bibliography, and sections documenting related work, experimental methods, and results; however, there is no effective way to extract this information due to their diverse layout. In this paper, we present a novel approach to developing an end-to-end learning framework to segment and classify major regions of a scientific document. We consider scientific document layout analysis as an object detection task over digital images, without any additional text features that need to be added into the network during the training process. Our technical objective is to implement transfer learning via fine-tuning of pre-trained networks and thereby demonstrate that this deep learning architecture is suitable for tasks that lack very large document corpora for training ab initio. As part of the experimental test bed for empirical evaluation of this approach, we created a merged multi-corpus data set for scientific publication layout detection tasks. Our results show good improvement with fine-tuning of a pre-trained base network using this merged data set, compared to the baseline convolutional neural network architecture.