PubTables-1M: Towards comprehensive table extraction from unstructured documents

Smock, Brandon; Rohith, Pesala,; Abraham, Robin

doi:10.48550/arxiv.2110.00061

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the experiments we use tables from the test set of the PubTables-1M [8] dataset, which provides text content and location information for every cell, including blank cells. To make sure each remaining grid cell has well-defined content and location after removing a subset of rows and columns from a table, we only use tables that do not contain any spanning cells.…”

Section: Methodsmentioning

confidence: 99%

“…Measures of partial correctness are useful not only because they are more granular, but also because they are less impacted by small errors and ambiguities in the ground truth. This is important, as creating unambiguous ground truth for table structure recognition is a challenging problem, which introduces noise not only into the learning task but also performance evaluation [8,9]. Designing a metric for partial table correctness has also proven challenging.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GriTS: Grid table similarity metric for table structure recognition

Smock¹,

Rohith²,

Abraham³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a new class of evaluation metric for table structure recognition, grid table similarity (GriTS). Unlike prior metrics, GriTS evaluates the correctness of a predicted table directly in its natural form as a matrix. To create a similarity measure between matrices, we generalize the two-dimensional largest common substructure (2D-LCS) problem, which is NP-hard, to the 2D most similar substructures (2D-MSS) problem and propose a polynomial-time heuristic for solving it. We validate empirically using the PubTables-1M dataset that comparison between matrices exhibits more desirable behavior than alternatives for table structure recognition evaluation. GriTS also unifies all three subtasks of cell topology recognition, cell location recognition, and cell content recognition within the same framework, which simplifies the evaluation and enables more meaningful comparisons across different types of structure recognition approaches. Code will be released at https://github.com/microsoft/table-transformer.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

GriTS: Grid table similarity metric for table structure recognition

Smock¹,

Rohith²,

Abraham³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A few samples from this dataset are shown in Figure 14. PubTables-1M [63] contains nearly one million tables from scientific articles, supports multiple input modalities and contains detailed header and location information for table structures, making it useful for a wide variety of modeling approaches. It also addresses a significant source of ground truth inconsistency observed in prior datasets called over-segmentation, using a novel canonicalization procedure.…”

Section: Uw-3 Tablementioning

confidence: 99%

“…Recently transformer-based models were applied to document layout analysis, Smock, Brandon et al [63] applied Carion et al [93] DEtection TRansformer framework, a transformer encoder-decoder architecture, to their table dataset for both table detection and structure recognition tasks. Xu et al [94] proposed a self-supervised pre-trained Document Image Transformer model using large-scale unlabeled text images for document analysis, including table detection…”

Section: The System Searches For Sequences Of Table-like Lines Based ...mentioning

confidence: 99%

Deep learning for table detection and structure recognition: A survey

Kasem¹,

Abdallah²,

Berendeyev³

et al. 2022

Preprint

View full text Add to dashboard Cite

Tables are everywhere, from scientific journals, papers, websites, and newspapers all the way to items we buy at the supermarket. Detecting them is thus of utmost importance to automatically understanding the content of a document. The performance of table detection has substantially increased thanks to the rapid development of deep learning networks. The goals of this survey are to provide a profound comprehension of the major developments in the field of Table Detection, offer insight into the different methodologies, and provide a systematic taxonomy of the different approaches. Furthermore, we provide an analysis of both classic and new applications in the field. Lastly, the datasets and source code of the existing models are organized to provide the reader with a compass on this vast literature. Finally, we go over the architecture of utilizing various object detection and table structure recognition methods to create an effective and efficient system, as well as a set of development trends to keep up with state-of-the-art algorithms and future research. We have also set up a public GitHub repository where we will be updating the most recent publications, open data, and source code. The GitHub repository is available at https://github.com/abdoelsayed2016/ table-detection-structure-recognition.

show abstract

From Detection to Application: Recent Advances in Understanding Scientific Tables and Figures

Huang,

Chen,

et al. 2024

ACM Comput. Surv.

View full text Add to dashboard Cite

Tables and figures are usually used to present information in a structured and visual way in scientific documents. Understanding the tables and figures in scientific documents is significant for a series of downstream tasks, such as academic search, scientific knowledge graphs, and so on. Existing studies mainly focus on detecting figures and tables from scientific documents, interpreting their semantics, and integrating them into downstream tasks. However, a systematic and comprehensive literature review on the mining and application of tables and figures in academic papers is still missing. In this article, we introduce the research framework and the whole pipeline for understanding tables and figures, including detection, structural analysis, interpretation, and application. We deliver a thorough analysis of benchmark datasets, recent techniques, and their pros and cons. Additionally, a quantitative analysis of the effectiveness of different models on popular benchmarks is presented. We further outline several important applications that exploit the semantics of scientific tables and figures. Finally, we highlight the challenges and some potential directions for future research. We believe this is the first comprehensive survey in understanding scientific tables and figures that covers the landscape from detection to application.

show abstract

PubTables-1M: Towards comprehensive table extraction from unstructured documents

Cited by 3 publications

References 0 publications

GriTS: Grid table similarity metric for table structure recognition

GriTS: Grid table similarity metric for table structure recognition

Deep learning for table detection and structure recognition: A survey

From Detection to Application: Recent Advances in Understanding Scientific Tables and Figures

Contact Info

Product

Resources

About