DeepPaperComposer: A Simple Solution for Training Data Preparation for Parsing Research Papers

Ling, Meng; Chen, Jian

doi:10.18653/v1/2020.sdp-1.10

Cited by 11 publications

(9 citation statements)

References 25 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We make use of metadata from this collection in our work to gather paper PDFs prior to automatic extraction. Conceptually, our new VIS30K extends this line of work by leveraging new image-based extraction methods [27] and search tools to make the figure and table data accessible.…”

Section: Related Workmentioning

confidence: 99%

“…After model prediction, we used heuristics in [27] to combine both models' results by merging the bounding boxes from Faster R-CNN (better localization) with any additional images/bounding boxes detected by YOLOv3 (better detection) into an initial set of labeled bounding boxes. We further tightened or expanded these bounding boxes to acquire accurate regions for each figure and table.…”

Section: Table Captionmentioning

confidence: 99%

See 1 more Smart Citation

VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications

Chen,

Ling,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present the VIS30K dataset, a collection of 29,689 images that represents 30 years of figures and tables from each track of the IEEE Visualization conference series (Vis, SciVis, InfoVis, VAST). VIS30K's comprehensive coverage of the scientific literature in visualization not only reflects the progress of the field but also enables researchers to study the evolution of the state-of-the-art and to find relevant work based on graphical content. We describe the dataset and our semi-automatic collection process, which couples convolutional neural networks (CNN) with curation. Extracting figures and tables semi-automatically allows us to verify that no images are overlooked or extracted erroneously. To improve quality further, we engaged in a peer-search process for high-quality figures from early IEEE Visualization papers. With the resulting data, we also contribute VISImageNavigator (VIN, visimagenavigator.github.io

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Table Captionmentioning

confidence: 99%

VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications

Chen,

Ling,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This dataset is also cross-linked to vispubdata [34] so one can find images by keyword search. Their open-source models [44] can make the subsequent data collection easier with minimum human intervention.…”

Section: Resources Focused On Collections Of Refereed Literaturementioning

confidence: 99%

Visualization Resources: A Starting Point

Liu,

Alharbi,

Best

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Visualization, as a vibrant field for researchers, practitioners, and higher educational institutions, is growing and evolving very rapidly. Tremendous progress has been made since 1987, the year often cited as the beginning of data visualization as a distinct field. As such, the number of visualization resources and the demand for those resources are increasing at a very fast pace. We present a collection of open visualization resources for all those with an interest in interactive data visualization and visual analytics. Because the number of resources is so large, we focus on collections of resources, of which there are already very many ranging from literature collections to collections of practitioner resources. We develop a novel classification of visualization resource collections based on the resource type, e.g. literaturebased, web-based, etc. The result is a helpful overview and details-on-demand of many useful resources. The collection offers a valuable jump-start for those seeking out data visualization resources from all backgrounds spanning from beginners such as students to teachers, practitioners, and researchers wishing to create their own advanced or novel visual designs.

show abstract

“…Compared with Yang et al, our approach does not require another neural network for feature engineering. Ling and Chen [25] also used a rendering solution and they randomized figure and table positions for extracting those two categories. Our work broadens this approach by randomizing many document structural parts to acquire both structural and semantic labels.…”

Section: Document Parts and Layout Analysismentioning

confidence: 99%

Document Domain Randomization for Deep Learning Document Layout Extraction

Ling,

Chen,

Möller

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present document domain randomization (DDR), the first successful transfer of CNNs trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document pages by modeling randomized textual and non-textual contents of interest, with userdefined layout and font styles to support joint learning of fine-grained classes. We demonstrate competitive results using our DDR approach to extract nine document classes from the benchmark CS-150 and papers published in two domains, namely annual meetings of Association for Computational Linguistics (ACL) and IEEE Visualization (VIS). We compare DDR to conditions of style mismatch, fewer or more noisy samples that are more easily obtained in the real world. We show that high-fidelity semantic information is not necessary to label semantic classes but style mismatch between train and test can lower model accuracy. Using smaller training samples had a slightly detrimental effect. Finally, network models still achieved high test accuracy when correct labels are diluted towards confusing labels; this behavior hold across several classes.

show abstract

DeepPaperComposer: A Simple Solution for Training Data Preparation for Parsing Research Papers

Cited by 11 publications

References 25 publications

VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications

VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications

Visualization Resources: A Starting Point

Document Domain Randomization for Deep Learning Document Layout Extraction

Contact Info

Product

Resources

About