Contract Metadata Identification in Czech Scanned Documents

D 2021

Contract Metadata Identification in Czech Scanned Documents

HA, Hien Thi, Aleš HORÁK and BUi MINH TUAN

Basic information

Original name

Contract Metadata Identification in Czech Scanned Documents

Authors

HA, Hien Thi (704 Viet Nam, belonging to the institution), Aleš HORÁK (203 Czech Republic, guarantor, belonging to the institution) and BUi MINH TUAN (704 Viet Nam)

Edition

Portugal, Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, p. 795-802, 8 pp. 2021

Publisher

The SciTePress Digital Library

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

URL

RIV identification code

RIV/00216224:14330/21:00121131

Organization unit

Faculty of Informatics

ISBN

978-989-758-484-8

DOI

http://dx.doi.org/10.5220/0010243807950802

UT WoS

000661455800087

Keywords in English

Information Extraction; Scanned Documents; Document Metadata; Contract Metadata Extraction; Czech

Abstract

V originále

Although nowadays digital-born documents are generally prevalent, exchange of business documents often consists in processing their scanned image form as a general human-readable format with one-to-one correspondence to paper documents. Bulk processing of such scanned documents then requires human intervention to extract and enter the main document metadata. In this paper, we present the design and evaluation of a contract processing module in the OCRMiner system. The information extraction process allows to combine layout properties with text analysis as input to a rule-based extraction with confidence score propagation. The first results are evaluated with public Czech contract documents reaching the item extraction accuracy of almost 88%.

Links

LM2018101, research and development project

Name: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy (Acronym: LINDAT/CLARIAH-CZ)

Investor: Ministry of Education, Youth and Sports of the CR

Citovat

HA, Hien Thi, Aleš HORÁK and BUi MINH TUAN. Contract Metadata Identification in Czech Scanned Documents. Online. In Ana Paula Rocha ; Luc Steels and Jaap van den Herik. Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART. Portugal: The SciTePress Digital Library, 2021, p. 795-802. ISBN 978-989-758-484-8. Available from: https://dx.doi.org/10.5220/0010243807950802.

@inproceedings{1741557,
   author = {Ha, Hien Thi and Horák, Aleš and Minh Tuan, BUi},
   address = {Portugal},
   booktitle = {Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
   doi = {http://dx.doi.org/10.5220/0010243807950802},
   editor = {Ana Paula Rocha ; Luc Steels and Jaap van den Herik},
   keywords = {Information Extraction; Scanned Documents; Document Metadata; Contract Metadata Extraction; Czech},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Portugal},
   isbn = {978-989-758-484-8},
   pages = {795-802},
   publisher = {The SciTePress Digital Library},
   title = {Contract Metadata Identification in Czech Scanned Documents},
   url = {https://www.scitepress.org/PublicationsDetail.aspx?ID=Alw3hhTLE1M=&t=1},
   year = {2021}
}

TY  - JOUR
ID  - 1741557
AU  - Ha, Hien Thi - Horák, Aleš - Minh Tuan, BUi
PY  - 2021
TI  - Contract Metadata Identification in Czech Scanned Documents
PB  - The SciTePress Digital Library
CY  - Portugal
SN  - 9789897584848
KW  - Information Extraction
KW  - Scanned Documents
KW  - Document Metadata
KW  - Contract Metadata Extraction
KW  - Czech
UR  - https://www.scitepress.org/PublicationsDetail.aspx?ID=Alw3hhTLE1M=&t=1
N2  - Although nowadays digital-born documents are generally prevalent, exchange of business documents often consists in processing their scanned image form as a general human-readable format with one-to-one correspondence to paper documents. Bulk processing of such scanned documents then requires human intervention to extract and enter the main document metadata. In this paper, we present the design and evaluation of a contract processing module in the OCRMiner system. The information extraction process allows to combine layout properties with text analysis as input to a rule-based extraction with confidence score propagation. The first results are evaluated with public Czech contract documents reaching the item extraction accuracy of almost 88%.
ER  -

HA, Hien Thi, Aleš HORÁK and BUi MINH TUAN. Contract Metadata Identification in Czech Scanned Documents. Online. In Ana Paula Rocha ; Luc Steels and Jaap van den Herik. \textit{Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART}. Portugal: The SciTePress Digital Library, 2021, p.~795-802. ISBN~978-989-758-484-8. Available from: https://dx.doi.org/10.5220/0010243807950802.

Detailed Information on Publication Record