Conference paper Open Access

An Analysis of the Performance of Named Entity Recognition over OCRed Documents

Hamdi, Ahmed; Jean-Caurant, Axel; Sidere, Nicolas; Coustaty, Mickael; Doucet, Antoine


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>The use of digital libraries requires an easy accessibility to documents which is strongly impacted by the quality of document indexing. Named entities are among the most important information to index digital documents. According to a recent study, 80% of the top 500 queries sent to a digital library portal contained at least one named entity [2]. However most digitized documents are indexed through their OCRed version which includes numerous errors that may hinder the access to them. Named Entity Recognition (NER) is the task that aims to locate important names in a given text and to categorize them into a set of predefined classes (person, location, organization). This paper aims to estimate the performance of NER systems through OCRed data. It exhaustively discusses NER errors arising from OCR errors; we studied the correlation between NER accuracy and OCR error rates and estimated the cost of character insertion, deletion and&nbsp;substitution in named entities. Results show that even if the OCR&nbsp;engine does contaminate named entities with errors, NER systems can overcome this issue and correctly recognise&nbsp;some of them.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "L3i Laboratory, University of La Rochelle", 
      "@type": "Person", 
      "name": "Hamdi, Ahmed"
    }, 
    {
      "affiliation": "L3i Laboratory, University of La Rochelle", 
      "@type": "Person", 
      "name": "Jean-Caurant, Axel"
    }, 
    {
      "affiliation": "L3i Laboratory, University of La Rochelle", 
      "@type": "Person", 
      "name": "Sidere, Nicolas"
    }, 
    {
      "affiliation": "L3i Laboratory, University of La Rochelle", 
      "@type": "Person", 
      "name": "Coustaty, Mickael"
    }, 
    {
      "affiliation": "L3i Laboratory, University of La Rochelle", 
      "@type": "Person", 
      "name": "Doucet, Antoine"
    }
  ], 
  "headline": "An Analysis of the Performance of Named Entity Recognition over OCRed Documents", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-06-02", 
  "url": "https://zenodo.org/record/3243344", 
  "@type": "ScholarlyArticle", 
  "keywords": [
    "Indexing,", 
    "OCR", 
    "Named Entity", 
    "Extraction", 
    "Digital Libraries"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3243344", 
  "@id": "https://doi.org/10.5281/zenodo.3243344", 
  "workFeatured": {
    "url": "https://2019.jcdl.org/", 
    "alternateName": "JCDL", 
    "location": "Urbana-Champaign, Illinois", 
    "@type": "Event", 
    "name": "ACM/IEEE JOINT CONFERENCE ON DIGITAL LIBRARIES"
  }, 
  "name": "An Analysis of the Performance of Named Entity Recognition over OCRed Documents"
}
1,065
707
views
downloads
All versions This version
Views 1,0651,067
Downloads 707707
Data volume 226.9 MB226.9 MB
Unique views 824826
Unique downloads 665665

Share

Cite as