TabbyPDF: Web-Based System for PDF Table Extraction

Shigarov, Alexey O.; Altaev, Andrey; Mikhailov, Andrey A.; Paramonov, Viacheslav; Cherkashin, Evgeniy A.

doi:10.1007/978-3-319-99972-2_20

Cited by 21 publications

(20 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 and Table 3 which are macro averaged and micro averaged scores. Tabby [27] is a rule-based approach that is designed to process PDF documents, meaning that it cannot deal with document images. GraphTSR [3] is a graph-based approach heavily relying on the position features, including the cell coordinates, cell center, cell size, and table size, but without using any visual features.…”

Section: Experiments Settings and Resultsmentioning

confidence: 99%

Table Structure Recognition with Conditional Attention

Xiao¹,

Şimşek²,

Kantarcı³

et al. 2022

Preprint

View full text Add to dashboard Cite

Tabular data in digital documents is widely used to express compact and important information for readers. However, it is challenging to parse tables from unstructured digital documents, such as PDFs and images, into machine-readable format because of the complexity of table structures and the missing of meta-information. Table Structure Recognition (TSR) problem aims to recognize the structure of a table and transform the unstructured tables into a structured and machine-readable format so that the tabular data can be further analysed by the down-stream tasks, such as semantic modeling and information retrieval. In this study, we hypothesize that a complicated table structure can be represented by a graph whose vertices and edges represent the cells and association between cells, respectively. Then we define the table structure recognition problem as a cell association classification problem and propose a conditional attention network (CATT-Net). The experimental results demonstrate the superiority of our proposed method over the state-of-the-art methods on various datasets. Besides, we investigate whether the alignment of a cell bounding box or a text-focused approach has more impact on the model performance. Due to the lack of public dataset annotations based on these two approaches, we further annotate the ICDAR2013 dataset providing both types of bounding boxes, which can be a new benchmark dataset for evaluating the methods in this field. Experimental results show that the alignment of a cell bounding box can help improve the Micro-averaged F1 score from 0.915 to 0.963, and the Macro-average F1 score from 0.787 to 0.923.

show abstract

Section: Experiments Settings and Resultsmentioning

confidence: 99%

Table Structure Recognition with Conditional Attention

Xiao¹,

Şimşek²,

Kantarcı³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Table extraction is considered as a part of table understanding [16], and conventionally consists of two steps [8]:…”

Section: B Methodsmentioning

confidence: 99%

“…Figure 1 illustrates an intuitive example of the performance of different existing methods, i.e. Adobe Acrobat DC and 1 https://github.com/Irene323/GFTE Tabby [8]. Both of them fail to give the correct result.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GFTE: Graph-Based Financial Table Extraction

Huang

Yan

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Tabular data is a crucial form of information expression, which can organize data in a standard structure for easy information retrieval and comparison. However, in financial industry and many other fields tables are often disclosed in unstructured digital files, e.g. Portable Document Format (PDF) and images, which are difficult to be extracted directly. In this paper, to facilitate deep learning based table extraction from unstructured digital files, we publish a standard Chinese dataset named FinTab, which contains more than 1,600 financial tables of diverse kinds and their corresponding structure representation in JSON. In addition, we propose a novel graph-based convolutional neural network model named GFTE as a baseline for future comparison. GFTE integrates image feature, position feature and textual feature together for precise edge prediction and reaches overall good results 1 .

show abstract

“…Many prior works focused on document layout including [19,20,25,27,29,30,39,40]. This prior work uses layout information to inform field extraction methods or in sequential models for information extraction.…”

Section: Related Workmentioning

confidence: 99%

DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction

Chua¹,

Duffy²

2021

Document Analysis and Recognition – ICDAR 2021

View full text Add to dashboard Cite

We combine deep learning and Conditional Probabilistic Context Free Grammars (CPCFG) to create an end-to-end system for extracting structured information from complex documents. For each class of documents, we create a CPCFG that describes the structure of the information to be extracted. Conditional probabilities are modeled by deep neural networks. We use this grammar to parse 2-D documents to directly produce structured records containing the extracted information. This system is trained end-to-end with (Document, Record) pairs. We apply this approach to extract information from scanned invoices achieving state-of-the-art results.

show abstract

TabbyPDF: Web-Based System for PDF Table Extraction

Cited by 21 publications

References 21 publications

Table Structure Recognition with Conditional Attention

Table Structure Recognition with Conditional Attention

GFTE: Graph-Based Financial Table Extraction

DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction

Contact Info

Product

Resources

About