NBoukachab commited on
Commit
840a046
·
1 Parent(s): c081ac5

Modif the README

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -49,19 +49,20 @@ Please refer to the PyLaia library page (https://pypi.org/project/pylaia/) to us
49
  # Cite us!
50
 
51
  ```bibtex
52
- @inproceedings{10.1007/978-3-031-06555-2_27,
53
- author = {Maarand, Martin and Beyer, Yngvil and K\r{a}sen, Andre and Fosseide, Knut T. and Kermorvant, Christopher},
54
- title = {A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Latin},
55
  year = {2022},
56
  isbn = {978-3-031-06554-5},
57
  publisher = {Springer-Verlag},
58
  address = {Berlin, Heidelberg},
59
- url = {https://doi.org/10.1007/978-3-031-06555-2_27},
60
- doi = {10.1007/978-3-031-06555-2_27},
 
61
  booktitle = {Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22–25, 2022, Proceedings},
62
- pages = {399413},
63
- numpages = {15},
64
- keywords = {Latin language, Open-source, Handwriting recognition},
65
  location = {La Rochelle, France}
66
  }
67
  ```
 
49
  # Cite us!
50
 
51
  ```bibtex
52
+ @inproceedings{10.1007/978-3-031-06555-2_29,
53
+ author = {Monroc, Claire Bizon and Miret, Blanche and Bonhomme, Marie-Laurence and Kermorvant, Christopher},
54
+ title = {A Comprehensive Study Of Open-Source Libraries For Named Entity Recognition On Handwritten Historical Documents},
55
  year = {2022},
56
  isbn = {978-3-031-06554-5},
57
  publisher = {Springer-Verlag},
58
  address = {Berlin, Heidelberg},
59
+ url = {https://doi.org/10.1007/978-3-031-06555-2_29},
60
+ doi = {10.1007/978-3-031-06555-2_29},
61
+ abstract = {In this paper, we propose an evaluation of several state-of-the-art open-source natural language processing (NLP) libraries for named entity recognition (NER) on handwritten historical documents: spaCy, Stanza and Flair. The comparison is carried out on three low-resource multilingual datasets of handwritten historical documents: HOME (a multilingual corpus of medieval charters), Balsac (a corpus of parish records from Quebec), and Esposalles (a corpus of marriage records in Catalan). We study the impact of the document recognition processes (text line detection and handwriting recognition) on the performance of the NER. We show that current off-the-shelf NER libraries yield state-of-the-art results, even on low-resource languages or multilingual documents using multilingual models. We show, in an end-to-end evaluation, that text line detection errors have a greater impact than handwriting recognition errors. Finally, we also report state-of-the-art results on the public Esposalles dataset.},
62
  booktitle = {Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22–25, 2022, Proceedings},
63
+ pages = {429444},
64
+ numpages = {16},
65
+ keywords = {Text line detection, Named entity recognition, Handwritten historical documents},
66
  location = {La Rochelle, France}
67
  }
68
  ```