Table understanding in structured documents

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10473073" target="_blank" >RIV/00216208:11320/19:10473073 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICDARW.2019.40098" target="_blank" >https://doi.org/10.1109/ICDARW.2019.40098</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICDARW.2019.40098" target="_blank" >10.1109/ICDARW.2019.40098</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Table understanding in structured documents

Popis výsledku v původním jazyce

Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract specific information from structurally different tables or table-like structures with one model. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on our newly presented dataset of pro forma invoices, invoices and debit note documents using this representation and propose multiple baselines to solve this labeling problem. We then propose a novel neural network model that achieves strong, practical results on the presented dataset and analyze the model performance and effects of graph convolutions and self-attention in detail.

Název v anglickém jazyce

Table understanding in structured documents

Popis výsledku anglicky

Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract specific information from structurally different tables or table-like structures with one model. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on our newly presented dataset of pro forma invoices, invoices and debit note documents using this representation and propose multiple baselines to solve this labeling problem. We then propose a novel neural network model that achieves strong, practical results on the presented dataset and analyze the model performance and effects of graph convolutions and self-attention in detail.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2019 INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION WORKSHOPS (ICDARW), VOL 5

ISBN

978-1-72815-054-3

ISSN

1520-5363

e-ISSN

—

Počet stran výsledku

7

Strana od-do

158-164

Název nakladatele

IEEE

Místo vydání

NEW YORK

Místo konání akce

Sydney

Datum konání akce

19. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000518786800027