Software Open Access

Pie Model for Classical French -- Part-of-Speech and Morphology (CATTEX2009-max)

Camps, Jean-Baptiste; Gabay, Simon; Clérice, Thibault; Cafiero, Florian


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "fra", 
    "@type": "Language", 
    "name": "French"
  }, 
  "description": "<p>Pie Model for Classical French, for Part-of-Speech and Morphology tags (CATTEX2009-max).</p>\n\n<p>Trained on a corpus of Classical French Theatre.</p>\n\n<p><strong>More information</strong>:</p>\n\n<p>- <em>corpus</em>: Camps, Jean-Baptiste, &amp; Cafiero, Florian. (2019). Stylometric Analysis of Classical French Theatre [Data set]. Zenodo. <a href=\"http://doi.org/10.5281/zenodo.3353421\">http://doi.org/10.5281/zenodo.3353421</a>.</p>\n\n<p>- F. Cafiero and J.B. Camps, Why Moli&egrave;re most likely did write his plays, <em>Science Advances</em>, 27 Nov 2019: Vol. 5, no. 11, eaax5489, DOI: 10.1126/sciadv.aax5489, <a href=\"https://advances.sciencemag.org/content/5/11/eaax5489/\">https://advances.sciencemag.org/content/5/11/eaax5489/</a>.</p>\n\n<p>- J.B. Camps, S. Gabay, Th. Cl&eacute;rice and F. Cafiero, Corpus and Models for Lemmatisation and POS-tagging of Classical French Theatre, to be published.</p>\n\n<p><strong>Current results on test data:</strong></p>\n\n<p>::: Evaluation report for task: pos :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9701<br>\n&nbsp; precision: 0.92<br>\n&nbsp; recall: 0.8964<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.9229<br>\n&nbsp; precision: 0.9203<br>\n&nbsp; recall: 0.9175<br>\n&nbsp; support: 934<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 0.8165<br>\n&nbsp; precision: 0.4798<br>\n&nbsp; recall: 0.4904<br>\n&nbsp; support: 218</p>\n\n<p>::: Evaluation report for task: MODE :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9818<br>\n&nbsp; precision: 0.8765<br>\n&nbsp; recall: 0.8517<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.84<br>\n&nbsp; precision: 0.8483<br>\n&nbsp; recall: 0.7612<br>\n&nbsp; support: 125<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 0.8211<br>\n&nbsp; precision: 0.7256<br>\n&nbsp; recall: 0.658<br>\n&nbsp; support: 218</p>\n\n<p><br>\n::: Classification report :::</p>\n\n<p>| target&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | precision | recall | f1-score | support |<br>\n|-------------|-----------|--------|----------|---------|<br>\n| MODE=con&nbsp;&nbsp;&nbsp; | 0.81&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.94&nbsp;&nbsp; | 0.87&nbsp;&nbsp;&nbsp;&nbsp; | 18&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| MODE=imp&nbsp;&nbsp;&nbsp; | 0.83&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.78&nbsp;&nbsp; | 0.80&nbsp;&nbsp;&nbsp;&nbsp; | 68&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| MODE=ind&nbsp;&nbsp;&nbsp; | 0.91&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.92&nbsp;&nbsp; | 0.92&nbsp;&nbsp;&nbsp;&nbsp; | 341&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| MODE=sub&nbsp;&nbsp;&nbsp; | 0.84&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.62&nbsp;&nbsp; | 0.71&nbsp;&nbsp;&nbsp;&nbsp; | 60&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| MODE=x&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp; | 3694&nbsp;&nbsp;&nbsp; |<br>\n| avg / total | 0.88&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.85&nbsp;&nbsp; | 0.86&nbsp;&nbsp;&nbsp;&nbsp; | 4181&nbsp;&nbsp;&nbsp; |</p>\n\n<p><br>\n::: Evaluation report for task: TEMPS :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9871<br>\n&nbsp; precision: 0.9305<br>\n&nbsp; recall: 0.9259<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.9135<br>\n&nbsp; precision: 0.623<br>\n&nbsp; recall: 0.6072<br>\n&nbsp; support: 104<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 0.8394<br>\n&nbsp; precision: 0.8693<br>\n&nbsp; recall: 0.5399<br>\n&nbsp; support: 218</p>\n\n<p><br>\n::: Classification report :::</p>\n\n<p>| target&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | precision | recall | f1-score | support |<br>\n|-------------|-----------|--------|----------|---------|<br>\n| TEMPS=fut&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.85&nbsp;&nbsp; | 0.91&nbsp;&nbsp;&nbsp;&nbsp; | 47&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| TEMPS=ipf&nbsp;&nbsp; | 0.93&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.88&nbsp;&nbsp; | 0.90&nbsp;&nbsp;&nbsp;&nbsp; | 16&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| TEMPS=psp&nbsp;&nbsp; | 0.80&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 0.89&nbsp;&nbsp;&nbsp;&nbsp; | 4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| TEMPS=pst&nbsp;&nbsp; | 0.95&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.91&nbsp;&nbsp; | 0.93&nbsp;&nbsp;&nbsp;&nbsp; | 334&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| TEMPS=x&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp; | 3780&nbsp;&nbsp;&nbsp; |<br>\n| avg / total | 0.93&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.93&nbsp;&nbsp; | 0.92&nbsp;&nbsp;&nbsp;&nbsp; | 4181&nbsp;&nbsp;&nbsp; |</p>\n\n<p><br>\n::: Evaluation report for task: PERS :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9859<br>\n&nbsp; precision: 0.9821<br>\n&nbsp; recall: 0.9668<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.942<br>\n&nbsp; precision: 0.9178<br>\n&nbsp; recall: 0.9188<br>\n&nbsp; support: 362<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 0.8394<br>\n&nbsp; precision: 0.9426<br>\n&nbsp; recall: 0.6344<br>\n&nbsp; support: 218</p>\n\n<p><br>\n::: Classification report :::</p>\n\n<p>| target&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | precision | recall | f1-score | support |<br>\n|-------------|-----------|--------|----------|---------|<br>\n| PERS.=1&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.96&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp; | 429&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| PERS.=2&nbsp;&nbsp;&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.97&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp; | 258&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| PERS.=3&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.94&nbsp;&nbsp; | 0.96&nbsp;&nbsp;&nbsp;&nbsp; | 410&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| PERS.=x&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp; | 3084&nbsp;&nbsp;&nbsp; |<br>\n| avg / total | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.97&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp; | 4181&nbsp;&nbsp;&nbsp; |</p>\n\n<p><br>\n::: Evaluation report for task: NOMB :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9797<br>\n&nbsp; precision: 0.9809<br>\n&nbsp; recall: 0.9733<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.7865<br>\n&nbsp; precision: 0.7511<br>\n&nbsp; recall: 0.6884<br>\n&nbsp; support: 192<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 0.8349<br>\n&nbsp; precision: 0.7918<br>\n&nbsp; recall: 0.7729<br>\n&nbsp; support: 218</p>\n\n<p><br>\n::: Classification report :::</p>\n\n<p>| target&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | precision | recall | f1-score | support |<br>\n|-------------|-----------|--------|----------|---------|<br>\n| NOMB.=p&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.95&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp; | 545&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| NOMB.=s&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp; | 1831&nbsp;&nbsp;&nbsp; |<br>\n| NOMB.=x&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp; | 1805&nbsp;&nbsp;&nbsp; |<br>\n| avg / total | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.97&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp; | 4181&nbsp;&nbsp;&nbsp; |</p>\n\n<p>::: Evaluation report for task: GENRE :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9749<br>\n&nbsp; precision: 0.969<br>\n&nbsp; recall: 0.9685<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.9118<br>\n&nbsp; precision: 0.9063<br>\n&nbsp; recall: 0.9208<br>\n&nbsp; support: 465<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 0.7385<br>\n&nbsp; precision: 0.7097<br>\n&nbsp; recall: 0.6977<br>\n&nbsp; support: 218</p>\n\n<p><br>\n::: Classification report :::</p>\n\n<p>| target&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | precision | recall | f1-score | support |<br>\n|-------------|-----------|--------|----------|---------|<br>\n| GENRE=f&nbsp;&nbsp;&nbsp;&nbsp; | 0.92&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.94&nbsp;&nbsp; | 0.93&nbsp;&nbsp;&nbsp;&nbsp; | 387&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| GENRE=m&nbsp;&nbsp;&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.94&nbsp;&nbsp; | 0.96&nbsp;&nbsp;&nbsp;&nbsp; | 940&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| GENRE=n&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp; | 45&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| GENRE=x&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp; | 2809&nbsp;&nbsp;&nbsp; |<br>\n| avg / total | 0.97&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.97&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp; | 4181&nbsp;&nbsp;&nbsp; |</p>\n\n<p><br>\n::: Evaluation report for task: CAS :::</p>\n\n<p>all:<br>\n&nbsp; accuracy: 0.9983<br>\n&nbsp; precision: 0.9957<br>\n&nbsp; recall: 0.9901<br>\n&nbsp; support: 4181<br>\nambiguous-tokens:<br>\n&nbsp; accuracy: 0.9648<br>\n&nbsp; precision: 0.9796<br>\n&nbsp; recall: 0.9692<br>\n&nbsp; support: 199<br>\nunknown-tokens:<br>\n&nbsp; accuracy: 1.0<br>\n&nbsp; precision: 1.0<br>\n&nbsp; recall: 1.0<br>\n&nbsp; support: 218</p>\n\n<p><br>\n::: Classification report :::</p>\n\n<p>| target&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | precision | recall | f1-score | support |<br>\n|-------------|-----------|--------|----------|---------|<br>\n| CAS=i&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp; | 46&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| CAS=n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp; | 190&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| CAS=r&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.98&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.96&nbsp;&nbsp; | 0.97&nbsp;&nbsp;&nbsp;&nbsp; | 128&nbsp;&nbsp;&nbsp;&nbsp; |<br>\n| CAS=x&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 1.00&nbsp;&nbsp; | 1.00&nbsp;&nbsp;&nbsp;&nbsp; | 3817&nbsp;&nbsp;&nbsp; |<br>\n| avg / total | 1.00&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; | 0.99&nbsp;&nbsp; | 0.99&nbsp;&nbsp;&nbsp;&nbsp; | 4181&nbsp;&nbsp;&nbsp; |</p>\n\n<p>&nbsp;</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "\u00c9cole nationale des chartes", 
      "@id": "https://orcid.org/0000-0003-0385-7037", 
      "@type": "Person", 
      "name": "Camps, Jean-Baptiste"
    }, 
    {
      "affiliation": "Universit\u00e9 de Neuch\u00e2tel", 
      "@id": "https://orcid.org/0000-0001-9094-4475", 
      "@type": "Person", 
      "name": "Gabay, Simon"
    }, 
    {
      "affiliation": "\u00c9cole nationale des chartes", 
      "@id": "https://orcid.org/0000-0003-1852-9204", 
      "@type": "Person", 
      "name": "Cl\u00e9rice, Thibault"
    }, 
    {
      "affiliation": "CNRS", 
      "@id": "https://orcid.org/0000-0002-1951-6942", 
      "@type": "Person", 
      "name": "Cafiero, Florian"
    }
  ], 
  "url": "https://zenodo.org/record/3701320", 
  "datePublished": "2020-03-04", 
  "keywords": [
    "Natural language processing", 
    "Part-of-speech tagging", 
    "Classical French", 
    "French Language", 
    "Deep Learning"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3701320", 
  "@id": "https://doi.org/10.5281/zenodo.3701320", 
  "@type": "SoftwareSourceCode", 
  "name": "Pie Model for Classical French -- Part-of-Speech and Morphology (CATTEX2009-max)"
}
20
393
views
downloads
All versions This version
Views 209
Downloads 393381
Data volume 9.3 GB9.0 GB
Unique views 157
Unique downloads 5950

Share

Cite as