@inproceedings{hazem-etal-2020-books,
title = "Books of Hours. the First Liturgical Data Set for Text Segmentation.",
author = "Hazem, Amir and
Daille, Beatrice and
Kermorvant, Christopher and
Stutzmann, Dominique and
Bonhomme, Marie-Laurence and
Maarand, Martin and
Boillet, M{\'e}lodie",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.97",
pages = "776--784",
abstract = "The Book of Hours was the bestseller of the late Middle Ages and Renaissance. It is a historical invaluable treasure, documenting the devotional practices of Christians in the late Middle Ages. Up to now, its textual content has been scarcely studied because of its manuscript nature, its length and its complex content. At first glance, it looks too standardized. However, the study of book of hours raises important challenges: (i) in image analysis, its often lavish ornamentation (illegible painted initials, line-fillers, etc.), abbreviated words, multilingualism are difficult to address in Handwritten Text Recognition (HTR); (ii) its hierarchical entangled structure offers a new field of investigation for text segmentation; (iii) in digital humanities, its textual content gives opportunities for historical analysis. In this paper, we provide the first corpus of books of hours, which consists of Latin transcriptions of 300 books of hours generated by Handwritten Text Recognition (HTR) - that is like Optical Character Recognition (OCR) but for handwritten and not printed texts. We designed a structural scheme of the book of hours and annotated manually two books of hours according to this scheme. Lastly, we performed a systematic evaluation of the main state of the art text segmentation approaches.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazem-etal-2020-books">
<titleInfo>
<title>Books of Hours. the First Liturgical Data Set for Text Segmentation.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hazem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Daille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Kermorvant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Stutzmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Laurence</namePart>
<namePart type="family">Bonhomme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Maarand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mélodie</namePart>
<namePart type="family">Boillet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The Book of Hours was the bestseller of the late Middle Ages and Renaissance. It is a historical invaluable treasure, documenting the devotional practices of Christians in the late Middle Ages. Up to now, its textual content has been scarcely studied because of its manuscript nature, its length and its complex content. At first glance, it looks too standardized. However, the study of book of hours raises important challenges: (i) in image analysis, its often lavish ornamentation (illegible painted initials, line-fillers, etc.), abbreviated words, multilingualism are difficult to address in Handwritten Text Recognition (HTR); (ii) its hierarchical entangled structure offers a new field of investigation for text segmentation; (iii) in digital humanities, its textual content gives opportunities for historical analysis. In this paper, we provide the first corpus of books of hours, which consists of Latin transcriptions of 300 books of hours generated by Handwritten Text Recognition (HTR) - that is like Optical Character Recognition (OCR) but for handwritten and not printed texts. We designed a structural scheme of the book of hours and annotated manually two books of hours according to this scheme. Lastly, we performed a systematic evaluation of the main state of the art text segmentation approaches.</abstract>
<identifier type="citekey">hazem-etal-2020-books</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.97</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>776</start>
<end>784</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Books of Hours. the First Liturgical Data Set for Text Segmentation.
%A Hazem, Amir
%A Daille, Beatrice
%A Kermorvant, Christopher
%A Stutzmann, Dominique
%A Bonhomme, Marie-Laurence
%A Maarand, Martin
%A Boillet, Mélodie
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F hazem-etal-2020-books
%X The Book of Hours was the bestseller of the late Middle Ages and Renaissance. It is a historical invaluable treasure, documenting the devotional practices of Christians in the late Middle Ages. Up to now, its textual content has been scarcely studied because of its manuscript nature, its length and its complex content. At first glance, it looks too standardized. However, the study of book of hours raises important challenges: (i) in image analysis, its often lavish ornamentation (illegible painted initials, line-fillers, etc.), abbreviated words, multilingualism are difficult to address in Handwritten Text Recognition (HTR); (ii) its hierarchical entangled structure offers a new field of investigation for text segmentation; (iii) in digital humanities, its textual content gives opportunities for historical analysis. In this paper, we provide the first corpus of books of hours, which consists of Latin transcriptions of 300 books of hours generated by Handwritten Text Recognition (HTR) - that is like Optical Character Recognition (OCR) but for handwritten and not printed texts. We designed a structural scheme of the book of hours and annotated manually two books of hours according to this scheme. Lastly, we performed a systematic evaluation of the main state of the art text segmentation approaches.
%U https://aclanthology.org/2020.lrec-1.97
%P 776-784
Markdown (Informal)
[Books of Hours. the First Liturgical Data Set for Text Segmentation.](https://aclanthology.org/2020.lrec-1.97) (Hazem et al., LREC 2020)
ACL
- Amir Hazem, Beatrice Daille, Christopher Kermorvant, Dominique Stutzmann, Marie-Laurence Bonhomme, Martin Maarand, and Mélodie Boillet. 2020. Books of Hours. the First Liturgical Data Set for Text Segmentation.. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 776–784, Marseille, France. European Language Resources Association.