Explainability and transparency in the realm of digital humanities: toward a historian XAI

The recent advancements in the field of Artificial Intelligence (AI) translated to an increased adoption of AI technology in the humanities, which is often challenged by the limited amount of annotated data, as well as its heterogeneity. Despite the scarcity of data it has become common practice to...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of digital humanities Vol. 5; no. 2-3; pp. 299 - 331
Main Authors El-Hajj, Hassan, Eberle, Oliver, Merklein, Anika, Siebold, Anna, Shlomi, Noga, Büttner, Jochen, Martinetz, Julius, Müller, Klaus-Robert, Montavon, Grégoire, Valleriani, Matteo
Format Journal Article
LanguageEnglish
Published Cham Springer International Publishing 01.11.2023
Subjects
Applied Statistics
Computational Linguistics
Cultural Studies
Digital/New Media
Mathematics and Statistics
Natural Language Processing (NLP)
Original Paper
Statistics
Computational humanities
Explainable AI
Digital humanities
Sphaera
Early modern printing
Online AccessGet full text
ISSN2524-7840
2524-7840
DOI10.1007/s42803-023-00070-1

Cover

Abstract The recent advancements in the field of Artificial Intelligence (AI) translated to an increased adoption of AI technology in the humanities, which is often challenged by the limited amount of annotated data, as well as its heterogeneity. Despite the scarcity of data it has become common practice to design increasingly complex AI models, usually at the expense of human readability, explainability, and trust. This in turn has led to an increased need for tools to help humanities scholars better explain and validate their models as well as their hypotheses. In this paper, we discuss the importance of employing Explainable AI (XAI) methods within the humanities to gain insights into historical processes as well as ensure model reproducibility and a trustworthy scientific result. To drive our point, we present several representative case studies from the Sphaera project where we analyze a large, well-curated corpus of early modern textbooks using an AI model, and rely on the XAI explanatory outputs to generate historical insights concerning their visual content. More specifically, we show that XAI can be used as a partner when investigating debated subjects in the history of science, such as what strategies were used in the early modern period to showcase mathematical instruments and machines.
AbstractList The recent advancements in the field of Artificial Intelligence (AI) translated to an increased adoption of AI technology in the humanities, which is often challenged by the limited amount of annotated data, as well as its heterogeneity. Despite the scarcity of data it has become common practice to design increasingly complex AI models, usually at the expense of human readability, explainability, and trust. This in turn has led to an increased need for tools to help humanities scholars better explain and validate their models as well as their hypotheses. In this paper, we discuss the importance of employing Explainable AI (XAI) methods within the humanities to gain insights into historical processes as well as ensure model reproducibility and a trustworthy scientific result. To drive our point, we present several representative case studies from the Sphaera project where we analyze a large, well-curated corpus of early modern textbooks using an AI model, and rely on the XAI explanatory outputs to generate historical insights concerning their visual content. More specifically, we show that XAI can be used as a partner when investigating debated subjects in the history of science, such as what strategies were used in the early modern period to showcase mathematical instruments and machines.
Author Martinetz, Julius
Müller, Klaus-Robert
El-Hajj, Hassan
Shlomi, Noga
Eberle, Oliver
Valleriani, Matteo
Siebold, Anna
Merklein, Anika
Montavon, Grégoire
Büttner, Jochen
Author_xml – sequence: 1
  givenname: Hassan
  surname: El-Hajj
  fullname: El-Hajj, Hassan
  email: hhajj@mpiwg-berlin.mpg.de
  organization: Max Planck Institute for the History of Science, BIFOLD – Berlin Institute for the Foundations of Learning and Data
– sequence: 2
  givenname: Oliver
  surname: Eberle
  fullname: Eberle, Oliver
  organization: BIFOLD – Berlin Institute for the Foundations of Learning and Data, Machine Learning Group, Technische Universität Berlin
– sequence: 3
  givenname: Anika
  surname: Merklein
  fullname: Merklein, Anika
  organization: Max Planck Institute for the History of Science
– sequence: 4
  givenname: Anna
  surname: Siebold
  fullname: Siebold, Anna
  organization: Max Planck Institute for the History of Science, German Center for Art History Paris (DFK Paris)
– sequence: 5
  givenname: Noga
  surname: Shlomi
  fullname: Shlomi, Noga
  organization: Max Planck Institute for the History of Science, The Cohn Institute for the History and Philosophy of Science and Ideas, Faculty of Humanities, Tel-Aviv University
– sequence: 6
  givenname: Jochen
  surname: Büttner
  fullname: Büttner, Jochen
  organization: Max Planck Institute for the History of Science
– sequence: 7
  givenname: Julius
  surname: Martinetz
  fullname: Martinetz, Julius
  organization: Max Planck Institute for the History of Science, BIFOLD – Berlin Institute for the Foundations of Learning and Data, Machine Learning Group, Technische Universität Berlin
– sequence: 8
  givenname: Klaus-Robert
  surname: Müller
  fullname: Müller, Klaus-Robert
  organization: BIFOLD – Berlin Institute for the Foundations of Learning and Data, Machine Learning Group, Technische Universität Berlin, Department of Artificial Intelligence, Korea University, Max Planck Institute for Informatics
– sequence: 9
  givenname: Grégoire
  surname: Montavon
  fullname: Montavon, Grégoire
  organization: BIFOLD – Berlin Institute for the Foundations of Learning and Data, Machine Learning Group, Technische Universität Berlin, Department of Mathematics and Computer Science, Freie Universität Berlin
– sequence: 10
  givenname: Matteo
  surname: Valleriani
  fullname: Valleriani, Matteo
  email: valleriani@mpiwg-berlin.mpg.de
  organization: Max Planck Institute for the History of Science, BIFOLD – Berlin Institute for the Foundations of Learning and Data, The Cohn Institute for the History and Philosophy of Science and Ideas, Faculty of Humanities, Tel-Aviv University, Institute of History and Philosophy of Science, Technology, and Literature, Faculty I, Technische Universität Berlin
BookMark eNp9kM9KAzEQh4NUsNa-gKe8wGqS3bhZb6VULRS8KIiXMJs_bco2W5IU3bc3Wg_ioYcwGZhvht93iUa-9waha0puKCH1bayYIGVBWH65JwU9Q2PGWVXUoiKjP_8LNI1xm4dYTQkT5Ri9Lz73HTgPretcGjB4jVMAH_cQjFcDdh6njcHBQLfDvcXarV2CDm8OO_AuORPvceo_IGgMeONi6oMDj99myyt0bqGLZvpbJ-j1YfEyfypWz4_L-WxVKCoILbhi3BBFy5o3GrjiitZgSqotbQWphQVuGsEI0w1tlW0beyeI5qxWlaEaWDlB7LhXhT7GYKzcB7eDMEhK5LcgeRQksyD5I0jSDIl_kMqxkut9Tu-602h5RGO-49cmyG1_CD5HPEV9Ae6EfOA
CitedBy_id crossref_primary_10_1145_3699963
crossref_primary_10_1007_s42803_023_00083_w
crossref_primary_10_1126_sciadv_adj1719
crossref_primary_10_1021_acs_jctc_4c01424
crossref_primary_10_1007_s42803_023_00078_7
Cites_doi 10.1109/TNNLS.2016.2599820
10.1145/129617.129621
10.1007/978-3-030-83356-5_1
10.1109/TPAMI.2016.2577031
10.1007/978-981-19-1018-0_23
10.1016/B978-0-32-396098-4.00008-9
10.1038/s41586-022-04448-z
10.1007/s11229-012-0176-x
10.18653/v1/2021.emnlp-main.384
10.1038/s42256-020-00236-4
10.1109/TPAMI.2020.3020738
10.1073/pnas.2003794117
10.1093/llc/fqx047
10.1007/978-3-030-28954-6_10
10.1016/j.dsp.2017.10.011
10.1038/s41467-019-08987-4
10.1007/978-3-030-28954-6_17
10.1109/ICDAR.2017.223
10.1016/j.dss.2010.12.003
10.1186/s40494-021-00618-w
10.1016/j.artint.2018.07.007
10.1109/CVPR.2016.91
10.1038/s42256-021-00303-4
10.1145/3503161.3548112
10.1109/JPROC.2021.3060483
10.1007/978-3-030-28954-6_18
10.1016/j.patcog.2016.11.008
10.1145/3386392.3399276
10.3390/app12199423
10.1016/j.neuroimage.2022.119504
10.1175/BAMS-D-20-0097.1
10.1109/ICDAR.2017.231
10.1142/9789811203244_0005
10.1016/j.jas.2021.105375
10.1371/journal.pone.0130140
10.1007/s11263-019-01228-7
10.1016/j.media.2022.102470
10.1145/3476887.3476893
10.1109/ICDAR.2019.00245
10.1007/978-3-031-04083-2_1
10.1175/BAMS-D-18-0195.1
10.1109/ICDAR.2017.111
10.24963/ijcai.2018/147
10.1109/ICDAR.2017.20
10.1109/ACCESS.2021.3110082
10.1007/s42454-020-00021-z
10.4324/9781003106531-1
10.1109/SIBGRAPI51738.2020.00016
10.1007/978-3-030-11012-3_54
10.1109/ICFHR2020.2020.00027
10.1162/coli_a_00481
10.1002/widm.1312
10.1016/j.semcancer.2018.07.001.
10.1093/oso/9780198823520.001.0001
10.26225/FDZH-X261
10.1093/llc/fqw045
10.1007/978-3-030-28954-6
10.3390/jimaging7120260
10.18653/v1/D19-1668
10.1007/978-3-319-24574-4_28
10.1007/978-3-030-86334-0_8
10.1109/TPAMI.2021.3115452
10.1086/663607
10.1007/s11263-015-0823-z
10.1515/opar-2020-0136
10.1109/BCI57258.2023.10078502
10.1038/s42256-019-0052-1
10.1007/s13222-022-00414-1
10.3390/jimaging8100285
10.1007/s13347-022-00558-8
ContentType Journal Article
Copyright The Author(s) 2023
Copyright_xml – notice: The Author(s) 2023
DBID C6C
AAYXX
CITATION
DOI 10.1007/s42803-023-00070-1
DatabaseName Springer Nature OA Free Journals
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: C6C
  name: Springer Nature OA Free Journals
  url: http://www.springeropen.com/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Statistics
EISSN 2524-7840
EndPage 331
ExternalDocumentID 10_1007_s42803_023_00070_1
GrantInformation_xml – fundername: Max Planck Institute for the History of Science (MPIWG) (2)
– fundername: Institute of Information and Communications Technology Planning and Evaluation (IITP) grants funded by the Korea Government
  grantid: 2019-0-00079
– fundername: The Rotenstreich fund
– fundername: Berlin Institute for the Foundation of Learning and Data
  grantid: 01IS18037A
– fundername: Max Planck Institute for the History of Science
GroupedDBID 0R~
406
AACDK
AAHNG
AAJBT
AASML
AATNV
AAUYE
ABAKF
ABECU
ABFTV
ABJNI
ABKCH
ABMQK
ABTEG
ABTKH
ABTMW
ACAOD
ACDTI
ACHSB
ACOKC
ACPIV
ACZOJ
ADKNI
ADTPH
ADURQ
ADYFF
AEFQL
AEMSY
AESKC
AFBBN
AFQWF
AGDGC
AGMZJ
AGQEE
AIGIU
AILAN
AITGF
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMXSW
AMYLF
AXYYD
BGNMA
C6C
DPUIP
EBLON
EBS
EJD
FIGPU
FNLPD
GGCAI
H13
IKXTQ
IWAJR
JZLTJ
KOV
LLZTM
M4Y
NPVJJ
NQJWS
NU0
PT4
ROL
RSV
SJYHP
SNE
SNPRN
SOHCF
SOJ
SRMVM
SSLCW
UOJIU
UTJUX
VEKWB
VFIZW
ZMTXR
AAYXX
ABBRH
ABDBE
ABFSG
ACSTC
AEZWR
AFDZB
AFHIU
AFOHR
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
ID FETCH-LOGICAL-c1801-5c25e0c13759da5c5c17ae31df1b8078fa5e98202d91bcfb9f680d527c4e1da23
IEDL.DBID C6C
ISSN 2524-7840
IngestDate Tue Jul 01 03:42:24 EDT 2025
Thu Apr 24 23:07:46 EDT 2025
Fri Feb 21 02:41:03 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2-3
Keywords Computational humanities
Explainable AI
Digital humanities
Sphaera
Early modern printing
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1801-5c25e0c13759da5c5c17ae31df1b8078fa5e98202d91bcfb9f680d527c4e1da23
OpenAccessLink https://doi.org/10.1007/s42803-023-00070-1
PageCount 33
ParticipantIDs crossref_primary_10_1007_s42803_023_00070_1
crossref_citationtrail_10_1007_s42803_023_00070_1
springer_journals_10_1007_s42803_023_00070_1
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 20231100
PublicationDateYYYYMMDD 2023-11-01
PublicationDate_xml – month: 11
  year: 2023
  text: 20231100
PublicationDecade 2020
PublicationPlace Cham
PublicationPlace_xml – name: Cham
PublicationTitle International journal of digital humanities
PublicationTitleAbbrev Int J Digit Humanities
PublicationYear 2023
Publisher Springer International Publishing
Publisher_xml – name: Springer International Publishing
References Díaz-Rodríguez, N., & Pisoni, G. (2020) Accessible cultural heritage through explainable artificial intelligence. In: Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization. UMAP ’20 Adjunct, pp. 317–324. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3386392.3399276
Shlomi, N. (2023). The Evolution of Visual Language in Early Modern Astronomy. Tel-Aviv University, The Cohn Institute for the History and Philosophy of Science and Ideas (in progress)
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation
JiFMcMasterMSSchwabSSinghGSmithLNAdhikariSO’DwyerMSayedFIngrisanoAYoderDBolmanESMartinITHinczewskiMSingerKDDiscerning the painter’s hand: machine learning on surface topographyHeritage Science20219115210.1186/s40494-021-00618-w
Piccolomini, A. (1553). Editione Tertia. Della Sfera del Mondo di M. Alisandro Piccolomini, Divisa in Libri Quattro, i Quali Non per Via di Traduttione, Ne à Qual si Voglia Particolare Scrittore Obligati, Ma Parte da Migliori Raccogliendo, e Parte di Nuovo Producendo, Contengano in Se Tutto Quel Ch’intorno à Tal Materia si Possa Desiderare, Ridotti a Tanta Agevolezza, et à Cosi Facil Modo di Dimostrare, Che Qual si Voglia Poco Essercitato Ne Gli Studij di Mathematica PotràAgevolißimamente, et Con Prestezza Incenderne Il Tutto. Di Nuovo Ricorretta, et Ampliata. Delle Stelle Fisse. Libro Uno Con Le sue Figure et Con Le sue Tavole, Dove Con Maravigliosa Agevolezza Potrà Ciascuno Conoscere Qualunque Stella delle Quarantaotto Imagini del Cielo Stellato, et Le Favole Loro Integramente, et Sapere in Ogni Tempo Del’anno, à Qual si Voglia Hora di Notte, in Che Parte del Cielo si Truovino, Non Solo Le Dette Imagini, Ma Qualunque Stella di Quelle. Bartolomeo Cesano, Venice. https://hdl.handle.net/21.11103/sphaera.101047
Berry, D. (2021). Explanatory publics: Explainability and democratic thought. In: B. Balaskas & C. Rito (Eds.), Fabricating Publics: The Dissemination of Culture in Post-truth Era (pp. 211–232). Open Humanities Press, Bristol
Flanders, J., & Jannidis, F. (2023). Knowledge organization and data modeling in the humanities
Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, K.-R., & Samek, W. (2022). xxai - beyond explainable artificial intelligence. In: A. Holzinger, R. Goebel, R. Fong, T. Moon, K.-R. Müller, & W. Samek (Eds.), xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, pp. 3–10. Springer, Cham. https://doi.org/10.1007/978-3-031-04083-2_1
da Firenze, M. (1537). Sphera Volgare Novamente Tradotta Con Molte Notande Additioni di Geometria, Cosmographia, Arte Navigatoria, et Stereometria, Proportioni, et Quantita Delli Elementi, Distanze, Grandeze, et Movimenti di Tutti Li Corpi Celesti, Cose Certamente Rade et Maravigliose. Autore M. Mauro Fiorentino Phonasco et Philopanareto. A Messer Giovan’Orthega Di Carion Burgense Hispano, et Dino Compagni Patritio Fiorentino, Mathematici. Bartolomeo Zanetti, Florence. https://hdl.handle.net/21.11103/sphaera.101009
BinderABockmayrMHägeleMWienertSHeimDHellwegKIshiiMStenzingerAHockeADenkertCMüllerK-RKlauschenFMorphological and molecular breast cancer profiling through explainable machine learningNature Machine Intelligence2021311210.1038/s42256-021-00303-4
Simistira, F., Bouillon, M., Seuret, M., Würsch, M., Alberti, M., Ingold, R., & Liwicki, M. (2017). Icdar2017 competition on layout analysis for challenging medieval manuscripts. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 1361–1370. https://doi.org/10.1109/ICDAR.2017.223
Hofmann S., Beyer F., Lapuschkin S., Goltermann O., Loeffler M., Robert-Müller K., Villringer A., Samek W., & Witter A. (2022). Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain. NeuroImage,261, 119504. https://doi.org/10.1016/j.neuroimage.2022.119504
Clausner, C., Antonacopoulos, A., & Pletschacher, S. (2019). Icdar2019 competition on recognition of documents with complex layouts - rdcl2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1521–1526. https://doi.org/10.1109/ICDAR.2019.00245
ZhangZChenPMcGoughMXingFWangCBuiMMXieYSapkotaMCuiLDhillonJAhmadNKhalilFKDickinsonSIShiXLiuFSuHCaiJYangLPathologist-level interpretable whole-slide cancer diagnosis with deep learningNature Machine Intelligence2019123624510.1038/s42256-019-0052-1
Barozzi, F. (1607). Cosmografia in Quattro Libri Divisa, la Quale Con Sommo Ordine, e Maravigliosa Facilitá, e Brevitá Introduce Alla Grande Mathematica Construttione di Tolomeo, & á Tutta l’Astrologia. Composta da Francesco Barozzi Gentil’huomo Venetiano. Con la Prefatione di Esso Autore, nella Quale si Ha Una Perfetta Divisione dell’Astrologia, & Una Narratione de Gli Autori Illustri, e De’ Volumi da Loro in Tutte Le Parti di Essa Composti: & si Mostrano 84 Errori di Gio. de Sacrobosco, & Molt’altri De’ Suoi Espositori, & Settatori, & Con Ragione si Riprendono. Preciede Ancho Alcuni Communi Mathematici, Arithmetici, & Geometrici Principij, Con Alcune Cose di Nuovo dall’Autore Ritrovate: & Alquante Propositioni, delle Quai per Tutta l’Opera si Fá Mentione: & Finalmente Un Indice Ricchissimo delle Cose in Essa Cosmografia Contenute. Grazioso Percacino, Venice. https://hdl.handle.net/21.11103/sphaera.100531
Jiménez-LunaJGrisoniFSchneiderGDrug discovery with explainable artificial intelligenceNature Machine Intelligence202010.1038/s42256-020-00236-4
Sacrobosco, J. d., & Melanchthon, P. (1545). Sphaera Ioannis de Sacrobosco Typis Auctior, Quam Antehac, Atque Ex Diligenti Manu Scriptorum Impressorumque Codicum Collatione Castigatior, Praemissa Philippi Melanchthonis Doctiss. Praefatione, Qua Utilitatem Astrologicae Scientiae, & Christiano Homini Non Negligendam Scite Probat. Jean Loys for Guillaume Richard, Paris. https://hdl.handle.net/21.11103/sphaera.101054
Puigcerver, J. (2017). Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 67–72. https://doi.org/10.1109/ICDAR.2017.20
Bluche, T., & Messina, R. (2017). Gated convolutional recurrent neural networks for multilingual handwriting recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 646–651. https://doi.org/10.1109/ICDAR.2017.111
Dutta, A., Bergel, G., & Zisserman, A. (2021). Visual analysis of chapbooks printed in scotland. In: The 6th International Workshop on Historical Document Imaging and Processing. HIP ’21, pp. 67–72. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3476887.3476893
JaderbergMSimonyanKVedaldiAZissermanAReading text in the wild with convolutional neural networksInternational Journal of Computer Vision20161161120344142210.1007/s11263-015-0823-z
Sacrobosco, J. d., & Clavius, C. (1585). Christophori Clavii Bambergensis Ex Societate Iesu in Sphaeram Ioannis de Sacro Bosco Commentarius Nunc Tertio Ab Ipso Auctore Recognitus, & Plerisque in Locis Locupletatus. Permissu Superiorem. Domenico Basa, Rome. https://hdl.handle.net/21.11103/sphaera.101120
EberleOBüttnerJKräutliFMüllerK-RVallerianiMMontavonGBuilding and interpreting deep similarity modelsIEEE Transactions on Pattern Analysis and Machine Intelligence20224431149116110.1109/TPAMI.2020.3020738
MontavonGSamekWMüllerK-RMethods for interpreting and understanding deep neural networksDigital Signal Processing201873115373787010.1016/j.dsp.2017.10.011
Sommerschield, T., Assael, Y., Pavlopoulos, J., Stefanak, V., Senior, A., Dyer, C., Bodel, J., Prag, J., Androutsopoulos, I., & Freitas, N.d. (2023). Machine Learning for Ancient Languages: A Survey. Computational Linguistics, 1–45. https://doi.org/10.1162/coli_a_00481
Bamman, D., & Burns, P.J. (2020). Latin BERT: A contextual language model for classical philology. CoRR abs/2009.10053 arXiv:2009.10053
Kralemann, B., & Lattmann, C. (2023). Models as icons: Modeling models in the semiotic framework of peirce’s theory of signs 190(16), 3397–3420. https://doi.org/10.1007/s11229-012-0176-x. Accessed 15 Feb 2023
BarucciACucciCFranciMLoschiavoMArgentiFA deep learning approach to ancient egyptian hieroglyphs classificationIEEE Access2021912343812344710.1109/ACCESS.2021.3110082
KräutliFVallerianiMCorpusTracer: A CIDOC database for tracing knowledge networksDSH201833233634610.1093/llc/fqx047
Müller, K.-R., & Hofmann, S. M. (2023). Interpreting deep learning models for multi-modal neuroimaging. In: 2023 11th International Winter Conference on Brain-Computer Interface (BCI), pp. 1–4. https://doi.org/10.1109/BCI57258.2023.10078502
Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2018). BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs/1810.04805 arXiv:1810.04805
Preuer, K., Klambauer, G., Rippmann, F., Hochreiter, S., & Unterthiner, T. (2019). Interpretable deep learning in drug discovery. In: W. Samek, G. Montavon, A. Vedaldi, L. K. Hansen, & K.-R. Müller (Eds.), Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (pp. 331–345). Springer, Cham. https://doi.org/10.1007/978-3-030-28954-6_18
Tsochatzidis, L., Symeonidis, S., Papazoglou, A., & Pratikakis, I. (2021). Htr for greek historical handwritten documents. Journal of Imaging7(12). https://doi.org/10.3390/jimaging7120260
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In: International Conference on Learning Representations (Poster)
Finé, O. (1551). Sphaera Mundi, Sive Cosmographia Quinque Recèns Auctis & Emendatis Absoluta: in Qua Tum Prima Astronomiae Pars, Tum Geographie, Ac Hydrographie Rudimenta Pertractantur. Authore Orontio Finaeo Delphinate, Regio Mathematicarum Lutetiae Professore. Michel Vascosan, Pari
70_CR36
70_CR38
LM Pawlowicz (70_CR66) 2021; 130
S Bach (70_CR3) 2015; 10
M Jaderberg (70_CR43) 2016; 116
70_CR31
70_CR33
70_CR32
70_CR35
70_CR34
RJ Oosterhoff (70_CR65) 2018
W Samek (70_CR83) 2021; 109
T Schnake (70_CR84) 2022; 44
70_CR26
70_CR25
S Lapuschkin (70_CR52) 2019; 10
70_CR29
70_CR20
70_CR22
70_CR21
70_CR24
70_CR23
G Montavon (70_CR61) 2018; 73
O Eberle (70_CR27) 2022; 44
70_CR59
70_CR58
70_CR100
T Miller (70_CR57) 2019; 267
70_CR50
70_CR53
70_CR55
70_CR54
J Jiménez-Luna (70_CR45) 2020
E Fetaya (70_CR30) 2020; 117
BHM van der Velden (70_CR95) 2022; 79
70_CR48
70_CR47
70_CR49
70_CR40
E Holder (70_CR37) 2021; 3
70_CR46
A Binder (70_CR14) 2021; 3
70_CR73
70_CR72
70_CR75
70_CR74
70_CR77
W Samek (70_CR82) 2017; 28
70_CR76
70_CR79
70_CR78
70_CR4
70_CR71
70_CR1
70_CR70
70_CR69
70_CR62
70_CR64
70_CR63
70_CR68
70_CR67
Y Assael (70_CR2) 2022; 603
70_CR15
F Ji (70_CR44) 2021; 9
70_CR17
70_CR16
70_CR19
70_CR18
G Montavon (70_CR60) 2017; 65
70_CR94
70_CR97
GH Subramanian (70_CR93) 1992; 35
70_CR96
70_CR11
70_CR98
70_CR13
70_CR12
A Barucci (70_CR6) 2021; 9
F Kräutli (70_CR51) 2018; 33
70_CR91
70_CR90
70_CR92
I Ebert-Uphoff (70_CR28) 2020; 101
Z Zhang (70_CR99) 2019; 1
70_CR8
70_CR7
A Holzinger (70_CR39) 2019; 9
70_CR86
70_CR5
70_CR85
70_CR88
70_CR87
70_CR9
70_CR89
JA Bennett (70_CR10) 1987
J Huysmans (70_CR42) 2011; 51
A McGovern (70_CR56) 2019; 100
70_CR80
J Huggett (70_CR41) 2021; 7
70_CR81
References_xml – reference: Bamman, D., & Burns, P.J. (2020). Latin BERT: A contextual language model for classical philology. CoRR abs/2009.10053 arXiv:2009.10053
– reference: Ebert-UphoffIHilburnKEvaluation, tuning, and interpretation of neural networks for working with images in meteorological applicationsBulletin of the American Meteorological Society2020101122149217010.1175/BAMS-D-20-0097.1
– reference: KräutliFVallerianiMCorpusTracer: A CIDOC database for tracing knowledge networksDSH201833233634610.1093/llc/fqx047
– reference: JiFMcMasterMSSchwabSSinghGSmithLNAdhikariSO’DwyerMSayedFIngrisanoAYoderDBolmanESMartinITHinczewskiMSingerKDDiscerning the painter’s hand: machine learning on surface topographyHeritage Science20219115210.1186/s40494-021-00618-w
– reference: Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, K.-R., & Samek, W. (2022). xxai - beyond explainable artificial intelligence. In: A. Holzinger, R. Goebel, R. Fong, T. Moon, K.-R. Müller, & W. Samek (Eds.), xxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, pp. 3–10. Springer, Cham. https://doi.org/10.1007/978-3-031-04083-2_1
– reference: PawlowiczLMDownumCEApplications of deep learning to decorated ceramic typology and classification: A case study using tusayan white ware from northeast arizonaJournal of Archaeological Science202113010.1016/j.jas.2021.105375
– reference: Lazar, K., Saret, B., Yehudai, A., Horowitz, W., Wasserman, N., & Stanovsky, G. (2021). Filling the gaps in Ancient Akkadian texts: A masked language modelling approach. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4682–4691. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic. https://doi.org/10.18653/v1/2021.emnlp-main.384. https://aclanthology.org/2021.emnlp-main.384
– reference: Bell, P., & Offert, F. (2021). Reflections on connoisseurship and computer vision. Journal of Art Historiography,24
– reference: Sacrobosco, J. d. (1547). Sphaera Iohannis de Sacrobosco. Martinus Nutius I for Jan Waen, Leuven. https://hdl.handle.net/21.11103/sphaera.100125
– reference: McGovernALagerquistRGagneDJJergensenGEElmoreKLHomeyerCRSmithTMaking the black box more transparent: Understanding the physical implications of machine learningBulletin of the American Meteorological Society2019100112175219910.1175/BAMS-D-18-0195.1
– reference: OosterhoffRJMaking Mathematical Culture: University and Print in the Circle of Lefèvre D’Étaples2018Oxford-Warburg StudiesOxford University Press, Oxford, UK10.1093/oso/9780198823520.001.0001
– reference: Zonca, V. (1607). Novo Teatro di Machine et Edificii. Appresso Pietro Bertelli, Padova
– reference: Li, M., Lv, T., Cui, L., Lu, Y., Florêncio, D.A.F., Zhang, C., Li, Z., & Wei, F. (2021). Trocr: Transformer-based optical character recognition with pre-trained models. CoRR abs/2109.10282 arXiv:2109.10282
– reference: Clausner, C., Antonacopoulos, A., & Pletschacher, S. (2019). Icdar2019 competition on recognition of documents with complex layouts - rdcl2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1521–1526. https://doi.org/10.1109/ICDAR.2019.00245
– reference: Piccolomini, A. (1553). Editione Tertia. Della Sfera del Mondo di M. Alisandro Piccolomini, Divisa in Libri Quattro, i Quali Non per Via di Traduttione, Ne à Qual si Voglia Particolare Scrittore Obligati, Ma Parte da Migliori Raccogliendo, e Parte di Nuovo Producendo, Contengano in Se Tutto Quel Ch’intorno à Tal Materia si Possa Desiderare, Ridotti a Tanta Agevolezza, et à Cosi Facil Modo di Dimostrare, Che Qual si Voglia Poco Essercitato Ne Gli Studij di Mathematica PotràAgevolißimamente, et Con Prestezza Incenderne Il Tutto. Di Nuovo Ricorretta, et Ampliata. Delle Stelle Fisse. Libro Uno Con Le sue Figure et Con Le sue Tavole, Dove Con Maravigliosa Agevolezza Potrà Ciascuno Conoscere Qualunque Stella delle Quarantaotto Imagini del Cielo Stellato, et Le Favole Loro Integramente, et Sapere in Ogni Tempo Del’anno, à Qual si Voglia Hora di Notte, in Che Parte del Cielo si Truovino, Non Solo Le Dette Imagini, Ma Qualunque Stella di Quelle. Bartolomeo Cesano, Venice. https://hdl.handle.net/21.11103/sphaera.101047
– reference: Bennett, J. (2011). Early modern mathematical instruments. Isis,102(4), 697–705. Accessed 11 July 2023
– reference: van der VeldenBHMKuijfHJGilhuijsKGAViergeverMAExplainable artificial intelligence (xai) in deep learning-based medical image analysisMedical Image Analysis20227910.1016/j.media.2022.102470
– reference: Xu, Y., Yin, F., Zhang, Z., Liu, C.-L. (2018). Multi-task layout analysis for historical handwritten documents using fully convolutional networks. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pp. 1057–1063. International Joint Conferences on Artificial Intelligence Organization, Stockholm, Sweden. https://doi.org/10.24963/ijcai.2018/147
– reference: Redmon, J., Divvala, S.K., Girshick, R.B., & Farhadi, A. (2015). You only look once: Unified, real-time object detection. CoRR abs/1506.02640 arXiv:1506.02640
– reference: MillerTExplanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence2019267138387451110.1016/j.artint.2018.07.007
– reference: SchnakeTEberleOLedererJNakajimaSSchüttKTMüllerK-RMontavonGHigher-order explanations of graph neural networks via relevant walksIEEE Transactions on Pattern Analysis and Machine Intelligence202244117581759610.1109/TPAMI.2021.3115452
– reference: SamekWMontavonGLapuschkinSAndersCJMüllerK-RExplaining deep neural networks and beyond: A review of methods and applicationsProceedings of the IEEE2021109324727810.1109/JPROC.2021.3060483
– reference: Yepes, A.J., Zhong, X., & Burdick, D. (2021). ICDAR 2021 Competition on Scientific Literature Parsing
– reference: Díaz-Rodríguez, N., & Pisoni, G. (2020) Accessible cultural heritage through explainable artificial intelligence. In: Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization. UMAP ’20 Adjunct, pp. 317–324. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3386392.3399276
– reference: Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation
– reference: Klauschen, F., Müller, K.-R., Binder, A., Bockmayr, M., Hägele, M., Seegerer, P., Wienert, S., Pruneri, G., de Maria, S., Badve, S., Michiels, S., Nielsen, T.O., Adams, S., Savas, P., Symmans, F., Willis, S., Gruosso, T., Park, M., Haibe-Kains, B., Gallas, B., Thompson, A.M., Cree, I., Sotiriou, C., Solinas, C., Preusser, M., Hewitt, S.M., Rimm, D., Viale, G., Loi, S., Loibl, S., Salgado, R., & Denkert, C. (2018). Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning. Seminars in Cancer Biology,52, 151–157. https://doi.org/10.1016/j.semcancer.2018.07.001. Immuno-oncological biomarkers
– reference: Sacrobosco, J. d., & Glogów, J. o. (1513). Introductorium Compendiosum in Tractatum Spere Materialis Magistri Joannis de Sacrobusto Quem Abbreviavit Ex Almagesti Sapientis Ptholomei Claudi Philosophi Alexandrini Ex Pheludio Progeniti per Magistrum Joannem Glogoviensem Foeliciter Recollectum. Florian Ungler for Jan Haller, Kraków. https://hdl.handle.net/21.11103/sphaera.100913
– reference: Schreckenfuchs, E.O., Regiomontanus, J., Sacrobosco, J.d. (1569). Erasmi Osvvaldi Schreckenfuchsii Commentaria, in Sphaeram Ioannis de Sacrobusto, Accuratissima, Quibus Non Solumea Quae in Autoris Contextu Sunt, Sed Alia Etiam Ad Sphaericam Doctrinam Necessaria, Explicantur: Tabularum Atque Constructio, Ex Suis Principiis per Demonstrationum Seriem Clarem Dilucide Atque Docetur. His Adiecti Sunt Eiusdem Autoris Canones, Quibus Usus Tabularum, Quae Operi Ex Libro Directionum Ioannis Regiomontani, Passim Inseruntur, Ad Pulcherrimas Inquisitiones Astronomicas, Luculentissime Continetur. Reliqua Ad Consummatam Doctrinam Hanc Pertinentia, Ex Illum Primo Mobili, Eadem Forma Edito, Petes. Heinrich Petri, Basel. https://hdl.handle.net/21.11103/sphaera.101080
– reference: Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2018). BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs/1810.04805 arXiv:1810.04805
– reference: Sacrobosco, J. d., & Clavius, C. (1585). Christophori Clavii Bambergensis Ex Societate Iesu in Sphaeram Ioannis de Sacro Bosco Commentarius Nunc Tertio Ab Ipso Auctore Recognitus, & Plerisque in Locis Locupletatus. Permissu Superiorem. Domenico Basa, Rome. https://hdl.handle.net/21.11103/sphaera.101120
– reference: Drucker, J. (2011). Humanities approaches to graphical display. Digital Humanities Quarterly,5(1)
– reference: Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
– reference: de Sousa Neto, A.F., Bezerra, B.L.D., Toselli, A.H., & Lima, E.B. (2020). Htr-flor: A deep learning system for offline handwritten text recognition. In: 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 54–61. https://doi.org/10.1109/SIBGRAPI51738.2020.00016
– reference: Berry, D. (2020). The explainability turn: Critical digital humanities and explanation. In: L. Estill, J. Guiliano, & C. Crompton (Eds.), DH2020 Book of Abstracts (pp. 459–461). ADHO, Ottawa
– reference: SamekWBinderAMontavonGLapuschkinSMüllerK-REvaluating the visualization of what a deep neural network has learnedIEEE Transactions on Neural Networks and Learning Systems2017281126602673372178210.1109/TNNLS.2016.2599820
– reference: SubramanianGHNosekJRaghunathanSPKanitkarSSA comparison of the decision table and treeCommun. ACM1992351899410.1145/129617.129621
– reference: Assael, Y., Sommerschield, T., & Prag, J. (2019). Restoring ancient text using deep learning: a case study on Greek epigraphy. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP), pp. 6368–6375. Association for Computational Linguistics, Hong Kong, China. https://doi.org/10.18653/v1/D19-1668. https://aclanthology.org/D19-1668
– reference: Ravichandra, S., Siva Sathya, S., & Lourdu Marie Sophie, S. (2022). Deep learning based document layout analysis on historical documents. In R. R. Rout, S. K. Ghosh, P. K. Jana, A. K. Tripathy, J. P. Sahoo, & K.-C. Li (Eds.), Advances in Distributed Computing and Machine Learning (pp. 271–281). Springer, Singapore
– reference: Ramelli, A. (1588). Le Diverse et Artificiose Machine del Capitano Agostino Ramelli Dal Ponte Della Tresia Ingegniero del Christianissimo Re di Francia et di Pollonia: Nelle Quali si Contengono Uarij et Industriosi Mouimenti, Degni Digrandißima Speculatione, per Cauarne Beneficio Infinito in Ogni Sorte D’operatione. In casa del Autore, Parigi
– reference: Samek, W. (2023). Chapter 2 - explainable deep learning: concepts, methods, and new developments. In: J. Benois-Pineau, R. Bourqui, D. Petkovic, & G. Quénot (Eds.), Explainable Deep Learning AI (pp. 7–33). Academic Press, London. https://doi.org/10.1016/B978-0-32-396098-4.00008-9
– reference: BennettJAThe Divided Circle: A History of Instruments for Astronomy Navigation and Surveying.1987Christie’s collectors libraryPhaidon Press, Michigan, USA
– reference: Wick, C., Zöllner, J., & Grüning, T. (2021). Transformer for handwritten text recognition using bidirectional post-decoding. In: J. Lladós, D. Lopresti, & S. Uchida (Eds.), Document Analysis and Recognition - ICDAR 2021 (pp. 112–126). Springer, Cham
– reference: Kamath, U., & Liu, J. (2021). Introduction to interpretability and explainability. In: Explainable Artificial Intelligence: An Introduction to Interpretable Machine Learning, pp. 1–26. Springer, Cham. https://doi.org/10.1007/978-3-030-83356-5_1
– reference: MontavonGSamekWMüllerK-RMethods for interpreting and understanding deep neural networksDigital Signal Processing201873115373787010.1016/j.dsp.2017.10.011
– reference: ZhangZChenPMcGoughMXingFWangCBuiMMXieYSapkotaMCuiLDhillonJAhmadNKhalilFKDickinsonSIShiXLiuFSuHCaiJYangLPathologist-level interpretable whole-slide cancer diagnosis with deep learningNature Machine Intelligence2019123624510.1038/s42256-019-0052-1
– reference: Hofmann S., Beyer F., Lapuschkin S., Goltermann O., Loeffler M., Robert-Müller K., Villringer A., Samek W., & Witter A. (2022). Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain. NeuroImage,261, 119504. https://doi.org/10.1016/j.neuroimage.2022.119504
– reference: Ströbel, P., Clematide, S., Hodel, T., & Volk, M. (2022). Transformer-based htr for historical documents. In: Workshop on Computational Methods in the Humanities 2022
– reference: BarucciACucciCFranciMLoschiavoMArgentiFA deep learning approach to ancient egyptian hieroglyphs classificationIEEE Access2021912343812344710.1109/ACCESS.2021.3110082
– reference: HuggettJAlgorithmic agency and autonomy in archaeological practiceOpen Archaeology202171417434434191410.1515/opar-2020-0136
– reference: Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In: ICLR
– reference: Kralemann, B., & Lattmann, C. (2023). Models as icons: Modeling models in the semiotic framework of peirce’s theory of signs 190(16), 3397–3420. https://doi.org/10.1007/s11229-012-0176-x. Accessed 15 Feb 2023
– reference: MontavonGLapuschkinSBinderASamekWMüllerK-RExplaining nonlinear classification decisions with deep taylor decompositionPattern Recognition20176521122210.1016/j.patcog.2016.11.008
– reference: Branca, G. (1629). Le Machine : Volume Nuovo et di Molto Artificio da Fare Effeta Maravigliosi Tanto Spiritali Quanto di Animale Operatione Arichito di Bellissime Figure Con Le Dichiarationi a Ciascuna di Esse in Lingua Volgare et Latina. Mascardi, Roma
– reference: Ciula, A., & Eide, O. (2016). Modelling in digital humanities: Signs in context 32. https://doi.org/10.1093/llc/fqw045
– reference: BachSBinderAMontavonGKlauschenFMüllerK-RSamekWOn pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagationPLOS ONE201510714610.1371/journal.pone.0130140
– reference: Puigcerver, J. (2017). Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 67–72. https://doi.org/10.1109/ICDAR.2017.20
– reference: Flanders, J., & Jannidis, F. (2023). Knowledge organization and data modeling in the humanities
– reference: LapuschkinSWäldchenSBinderAMontavonGSamekWMüllerK-RUnmasking Clever Hans predictors and assessing what machines really learnNature Communications201910109610.1038/s41467-019-08987-4
– reference: Müller, K.-R., & Hofmann, S. M. (2023). Interpreting deep learning models for multi-modal neuroimaging. In: 2023 11th International Winter Conference on Brain-Computer Interface (BCI), pp. 1–4. https://doi.org/10.1109/BCI57258.2023.10078502
– reference: Finé, O. (1587). Opere di Orontio Fineo del Delfinato: Divise in Cinque Parti; Arimetica, Geometria, Cosmografia, et Orivoli, Tradotte da Cosimo Bartoli, Gentilhuomo, et Academico Fiorentino: Et Gli Specchi, Tradotti Dal Cavalier Ercole Bottrigaro, Gentilhuomo Bolognese. Nuovamente Poste in Luce. Francesco de Franceschi, Venice. https://hdl.handle.net/21.11103/sphaera.101202
– reference: Huang, Y., Lv, T., Cui, L., Lu, Y., & Wei, F. (2022). Layoutlmv3: Pre-training for document ai with unified text and image masking. In: Proceedings of the 30th ACM international conference on multimedia. MM ’22, pp. 4083–4091. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3503161.3548112
– reference: Sommerschield, T., Assael, Y., Pavlopoulos, J., Stefanak, V., Senior, A., Dyer, C., Bodel, J., Prag, J., Androutsopoulos, I., & Freitas, N.d. (2023). Machine Learning for Ancient Languages: A Survey. Computational Linguistics, 1–45. https://doi.org/10.1162/coli_a_00481
– reference: Cortés, M. (1556). Breve Compendio de la Sphera Y de la Arte de Navegar, Con Nueuos Instrumentos Y Reglas, Exemplificado Con Muy Subtiles Demonstraciones: Compuesto Por Martin Cortes Natural de Burjalaros en el Reyno de Aragon Y de Presente Vezino de la Ciudad de Cadiz: Dirigido al Invictissimo Monarcha Carlo Quinto Rey de las Hespanas Etc. Senor Nuestro. António Alvares, Seville. https://hdl.handle.net/21.11103/sphaera.101394
– reference: El-Hajj, H., Zamani, M., Büttner, J., Martinetz, J., Eberle, O., Shlomi, N., Siebold, A., Montavon, G., Müller, K.-R., Kantz, H., & Valleriani, M. (2022). An ever-expanding humanities knowledge graph: The sphaera corpus at the intersection of humanities, data management, and machine learning. Datenbank-Spektrum: Zeitschrift für Datenbanktechnologien und Information Retrieval. https://doi.org/10.1007/s13222-022-00414-1
– reference: Preuer, K., Klambauer, G., Rippmann, F., Hochreiter, S., & Unterthiner, T. (2019). Interpretable deep learning in drug discovery. In: W. Samek, G. Montavon, A. Vedaldi, L. K. Hansen, & K.-R. Müller (Eds.), Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (pp. 331–345). Springer, Cham. https://doi.org/10.1007/978-3-030-28954-6_18
– reference: HolzingerALangsGDenkHZatloukalKMüllerHCausability and explainability of artificial intelligence in medicineWIREs Data Mining and Knowledge Discovery201994131210.1002/widm.1312
– reference: HuysmansJDejaegerKMuesCVanthienenJBaesensBAn empirical evaluation of the comprehensibility of decision table, tree and rule based predictive modelsDecision Support Systems201151114115410.1016/j.dss.2010.12.003
– reference: Schütt, K. T., Gastegger, M., Tkatchenko, A., & Müller, K.-R. (2019). Quantum-chemical insights from interpretable atomistic neural networks. In: W. Samek, G. Montavon, A. Vedaldi, L. K. Hansen, & K.-R. Müller (Eds.), Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (pp. 311–330). Springer, Cham. https://doi.org/10.1007/978-3-030-28954-6_17
– reference: EberleOBüttnerJKräutliFMüllerK-RVallerianiMMontavonGBuilding and interpreting deep similarity modelsIEEE Transactions on Pattern Analysis and Machine Intelligence20224431149116110.1109/TPAMI.2020.3020738
– reference: Kang, L., Riba, P., Rusiñol, M., Fornés, A., & Villegas, M. (2020). Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition
– reference: JaderbergMSimonyanKVedaldiAZissermanAReading text in the wild with convolutional neural networksInternational Journal of Computer Vision20161161120344142210.1007/s11263-015-0823-z
– reference: Büttner, J., Martinetz, J., El-Hajj, H., & Valleriani, M. (2022). Cordeep and the sacrobosco dataset: Detection of visual elements in historical documents. Journal of Imaging,8(285). https://doi.org/10.3390/jimaging8100285
– reference: Ratti, E. (2022). Integrating artificial intelligence in scientific practice: Explicable AI as an interface. Philosophy and Technology,35(3). https://doi.org/10.1007/s13347-022-00558-8
– reference: Simistira, F., Bouillon, M., Seuret, M., Würsch, M., Alberti, M., Ingold, R., & Liwicki, M. (2017). Icdar2017 competition on layout analysis for challenging medieval manuscripts. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 1361–1370. https://doi.org/10.1109/ICDAR.2017.223
– reference: Barozzi, F. (1607). Cosmografia in Quattro Libri Divisa, la Quale Con Sommo Ordine, e Maravigliosa Facilitá, e Brevitá Introduce Alla Grande Mathematica Construttione di Tolomeo, & á Tutta l’Astrologia. Composta da Francesco Barozzi Gentil’huomo Venetiano. Con la Prefatione di Esso Autore, nella Quale si Ha Una Perfetta Divisione dell’Astrologia, & Una Narratione de Gli Autori Illustri, e De’ Volumi da Loro in Tutte Le Parti di Essa Composti: & si Mostrano 84 Errori di Gio. de Sacrobosco, & Molt’altri De’ Suoi Espositori, & Settatori, & Con Ragione si Riprendono. Preciede Ancho Alcuni Communi Mathematici, Arithmetici, & Geometrici Principij, Con Alcune Cose di Nuovo dall’Autore Ritrovate: & Alquante Propositioni, delle Quai per Tutta l’Opera si Fá Mentione: & Finalmente Un Indice Ricchissimo delle Cose in Essa Cosmografia Contenute. Grazioso Percacino, Venice. https://hdl.handle.net/21.11103/sphaera.100531
– reference: Fischer, A. (2020). Automatic handwriting recognition in historical documents. In: A. Fischer, M. Liwicki, & R. Ingold (Eds.), Handwritten Historical Document Analysis, Recognition, and Retrieval - State of the Art and Future Trends (pp. 67–80). World Scientific, Friboug, Switzerland
– reference: Besson, J. (1595). Theatrum Oder Schawbuch Allerley Werckzeug und Rüstungen. Foillet, Mümbelgart
– reference: Dutta, A., Bergel, G., & Zisserman, A. (2021). Visual analysis of chapbooks printed in scotland. In: The 6th International Workshop on Historical Document Imaging and Processing. HIP ’21, pp. 67–72. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3476887.3476893
– reference: Offert, F. (2018). Images of image machines. visual interpretability in computer vision for art. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops
– reference: Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In: International Conference on Learning Representations (Poster)
– reference: Sacrobosco, J. d., & Melanchthon, P. (1545). Sphaera Ioannis de Sacrobosco Typis Auctior, Quam Antehac, Atque Ex Diligenti Manu Scriptorum Impressorumque Codicum Collatione Castigatior, Praemissa Philippi Melanchthonis Doctiss. Praefatione, Qua Utilitatem Astrologicae Scientiae, & Christiano Homini Non Negligendam Scite Probat. Jean Loys for Guillaume Richard, Paris. https://hdl.handle.net/21.11103/sphaera.101054
– reference: Jiménez-LunaJGrisoniFSchneiderGDrug discovery with explainable artificial intelligenceNature Machine Intelligence202010.1038/s42256-020-00236-4
– reference: Bluche, T., & Messina, R. (2017). Gated convolutional recurrent neural networks for multilingual handwriting recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 646–651. https://doi.org/10.1109/ICDAR.2017.111
– reference: Gao, L., Yi, X., Jiang, Z., Hao, L., & Tang, Z. (2017). Icdar2017 competition on page object detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 1417–1422. https://doi.org/10.1109/ICDAR.2017.231
– reference: Tsochatzidis, L., Symeonidis, S., Papazoglou, A., & Pratikakis, I. (2021). Htr for greek historical handwritten documents. Journal of Imaging7(12). https://doi.org/10.3390/jimaging7120260
– reference: FetayaELifshitzYAaronEGordinSRestoration of fragmentary babylonian texts using recurrent neural networksProceedings of the National Academy of Sciences202011737227432275110.1073/pnas.2003794117
– reference: Bekiari, C., Bruseke, G., Doerr, M., Ore, C.-E., Stead, S., & Velios, A. (2021). Definition of the cidoc conceptual reference model v7.1.1. The CIDOC Conceptual Reference Model Special Interest Group. https://doi.org/10.26225/FDZH-X261
– reference: BinderABockmayrMHägeleMWienertSHeimDHellwegKIshiiMStenzingerAHockeADenkertCMüllerK-RKlauschenFMorphological and molecular breast cancer profiling through explainable machine learningNature Machine Intelligence2021311210.1038/s42256-021-00303-4
– reference: Monnier, T., & Aubry, M. (2020). docExtractor: An off-the-shelf historical document element extraction. In: ICFHR
– reference: Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020). Grad-cam: Visual explanations from deep networks via gradient-based localization 128, 336–359. https://doi.org/10.1007/s11263-019-01228-7
– reference: da Firenze, M. (1537). Sphera Volgare Novamente Tradotta Con Molte Notande Additioni di Geometria, Cosmographia, Arte Navigatoria, et Stereometria, Proportioni, et Quantita Delli Elementi, Distanze, Grandeze, et Movimenti di Tutti Li Corpi Celesti, Cose Certamente Rade et Maravigliose. Autore M. Mauro Fiorentino Phonasco et Philopanareto. A Messer Giovan’Orthega Di Carion Burgense Hispano, et Dino Compagni Patritio Fiorentino, Mathematici. Bartolomeo Zanetti, Florence. https://hdl.handle.net/21.11103/sphaera.101009
– reference: Montavon, G., Binder, A., Lapuschkin, S., Samek, W., & Müller, K.-R. (2019). Layer-wise relevance propagation: An overview. In: Explainable AI, pp. 193–209. Springer, Cham. https://doi.org/10.1007/978-3-030-28954-6_10
– reference: Finé, O. (1551). Sphaera Mundi, Sive Cosmographia Quinque Recèns Auctis & Emendatis Absoluta: in Qua Tum Prima Astronomiae Pars, Tum Geographie, Ac Hydrographie Rudimenta Pertractantur. Authore Orontio Finaeo Delphinate, Regio Mathematicarum Lutetiae Professore. Michel Vascosan, Paris. https://hdl.handle.net/21.11103/sphaera.101206
– reference: HolderEWangNExplainable artificial intelligence (xai) interactively working with humans as a junior cyber analystHuman-Intelligent Systems Integration2021313915310.1007/s42454-020-00021-z
– reference: Narayanan, M., Chen, E., He, J., Kim, B., Gershman, S., & Doshi-Velez, F. (2018). How do humans understand explanations from machine learning systems? An evaluation of the human-interpretability of explanation
– reference: Shlomi, N. (2023). The Evolution of Visual Language in Early Modern Astronomy. Tel-Aviv University, The Cohn Institute for the History and Philosophy of Science and Ideas (in progress)
– reference: Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K., & Müller, K.-R. (Eds.) (2019). Explainable AI: Interpreting, Explaining and Visualizing Deep Learning Lecture Notes in Computer Science, Vol. 11700. Springer, Cham
– reference: Berry, D. (2021). Explanatory publics: Explainability and democratic thought. In: B. Balaskas & C. Rito (Eds.), Fabricating Publics: The Dissemination of Culture in Post-truth Era (pp. 211–232). Open Humanities Press, Bristol
– reference: AssaelYSommerschieldTSchillingfordBBodbarMPavlopoulosJChatzipanangiotouMAndroutsopulosIPragJde FreitasNRestoring and attributing ancient texts using deep neural networksNature202260328028310.1038/s41586-022-04448-z
– reference: Lopes, P., Silve, E., Barga, C., Oliveira, T., & Rosado, L. (2023). Xai systems evaluation: A review of human nad computer-centered methods. Applied Science,12(19)
– volume: 28
  start-page: 2660
  issue: 11
  year: 2017
  ident: 70_CR82
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2016.2599820
– ident: 70_CR23
– volume: 35
  start-page: 89
  issue: 1
  year: 1992
  ident: 70_CR93
  publication-title: Commun. ACM
  doi: 10.1145/129617.129621
– ident: 70_CR4
– ident: 70_CR46
  doi: 10.1007/978-3-030-83356-5_1
– ident: 70_CR74
  doi: 10.1109/TPAMI.2016.2577031
– ident: 70_CR20
– ident: 70_CR72
  doi: 10.1007/978-981-19-1018-0_23
– ident: 70_CR80
  doi: 10.1016/B978-0-32-396098-4.00008-9
– ident: 70_CR78
– volume: 603
  start-page: 280
  year: 2022
  ident: 70_CR2
  publication-title: Nature
  doi: 10.1038/s41586-022-04448-z
– ident: 70_CR50
  doi: 10.1007/s11229-012-0176-x
– ident: 70_CR53
  doi: 10.18653/v1/2021.emnlp-main.384
– year: 2020
  ident: 70_CR45
  publication-title: Nature Machine Intelligence
  doi: 10.1038/s42256-020-00236-4
– volume: 44
  start-page: 1149
  issue: 3
  year: 2022
  ident: 70_CR27
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2020.3020738
– volume: 117
  start-page: 22743
  issue: 37
  year: 2020
  ident: 70_CR30
  publication-title: Proceedings of the National Academy of Sciences
  doi: 10.1073/pnas.2003794117
– volume: 33
  start-page: 336
  issue: 2
  year: 2018
  ident: 70_CR51
  publication-title: DSH
  doi: 10.1093/llc/fqx047
– ident: 70_CR12
– ident: 70_CR59
  doi: 10.1007/978-3-030-28954-6_10
– ident: 70_CR92
– volume: 73
  start-page: 1
  year: 2018
  ident: 70_CR61
  publication-title: Digital Signal Processing
  doi: 10.1016/j.dsp.2017.10.011
– volume: 10
  start-page: 1096
  year: 2019
  ident: 70_CR52
  publication-title: Nature Communications
  doi: 10.1038/s41467-019-08987-4
– ident: 70_CR77
– ident: 70_CR54
– ident: 70_CR86
  doi: 10.1007/978-3-030-28954-6_17
– ident: 70_CR89
  doi: 10.1109/ICDAR.2017.223
– volume: 51
  start-page: 141
  issue: 1
  year: 2011
  ident: 70_CR42
  publication-title: Decision Support Systems
  doi: 10.1016/j.dss.2010.12.003
– volume: 9
  start-page: 152
  issue: 1
  year: 2021
  ident: 70_CR44
  publication-title: Heritage Science
  doi: 10.1186/s40494-021-00618-w
– volume: 267
  start-page: 1
  year: 2019
  ident: 70_CR57
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2018.07.007
– ident: 70_CR73
  doi: 10.1109/CVPR.2016.91
– volume: 3
  start-page: 1
  year: 2021
  ident: 70_CR14
  publication-title: Nature Machine Intelligence
  doi: 10.1038/s42256-021-00303-4
– ident: 70_CR40
  doi: 10.1145/3503161.3548112
– volume: 109
  start-page: 247
  issue: 3
  year: 2021
  ident: 70_CR83
  publication-title: Proceedings of the IEEE
  doi: 10.1109/JPROC.2021.3060483
– ident: 70_CR68
  doi: 10.1007/978-3-030-28954-6_18
– ident: 70_CR32
– volume: 65
  start-page: 211
  year: 2017
  ident: 70_CR60
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2016.11.008
– ident: 70_CR24
  doi: 10.1145/3386392.3399276
– ident: 70_CR5
– ident: 70_CR100
– ident: 70_CR55
  doi: 10.3390/app12199423
– ident: 70_CR88
– ident: 70_CR36
  doi: 10.1016/j.neuroimage.2022.119504
– volume: 101
  start-page: 2149
  issue: 12
  year: 2020
  ident: 70_CR28
  publication-title: Bulletin of the American Meteorological Society
  doi: 10.1175/BAMS-D-20-0097.1
– ident: 70_CR63
– ident: 70_CR21
– ident: 70_CR35
  doi: 10.1109/ICDAR.2017.231
– ident: 70_CR33
  doi: 10.1142/9789811203244_0005
– volume: 130
  year: 2021
  ident: 70_CR66
  publication-title: Journal of Archaeological Science
  doi: 10.1016/j.jas.2021.105375
– volume: 10
  start-page: 1
  issue: 7
  year: 2015
  ident: 70_CR3
  publication-title: PLOS ONE
  doi: 10.1371/journal.pone.0130140
– ident: 70_CR87
  doi: 10.1007/s11263-019-01228-7
– volume: 79
  year: 2022
  ident: 70_CR95
  publication-title: Medical Image Analysis
  doi: 10.1016/j.media.2022.102470
– ident: 70_CR26
  doi: 10.1145/3476887.3476893
– ident: 70_CR19
  doi: 10.1109/ICDAR.2019.00245
– ident: 70_CR38
  doi: 10.1007/978-3-031-04083-2_1
– ident: 70_CR8
– ident: 70_CR85
– volume-title: The Divided Circle: A History of Instruments for Astronomy Navigation and Surveying.
  year: 1987
  ident: 70_CR10
– ident: 70_CR13
– volume: 100
  start-page: 2175
  issue: 11
  year: 2019
  ident: 70_CR56
  publication-title: Bulletin of the American Meteorological Society
  doi: 10.1175/BAMS-D-18-0195.1
– ident: 70_CR15
  doi: 10.1109/ICDAR.2017.111
– ident: 70_CR76
– ident: 70_CR47
– ident: 70_CR97
  doi: 10.24963/ijcai.2018/147
– ident: 70_CR69
  doi: 10.1109/ICDAR.2017.20
– ident: 70_CR16
– volume: 9
  start-page: 123438
  year: 2021
  ident: 70_CR6
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3110082
– volume: 3
  start-page: 139
  year: 2021
  ident: 70_CR37
  publication-title: Human-Intelligent Systems Integration
  doi: 10.1007/s42454-020-00021-z
– ident: 70_CR25
  doi: 10.4324/9781003106531-1
– ident: 70_CR22
  doi: 10.1109/SIBGRAPI51738.2020.00016
– ident: 70_CR64
  doi: 10.1007/978-3-030-11012-3_54
– ident: 70_CR58
  doi: 10.1109/ICFHR2020.2020.00027
– ident: 70_CR79
– ident: 70_CR91
  doi: 10.1162/coli_a_00481
– volume: 9
  start-page: 1312
  issue: 4
  year: 2019
  ident: 70_CR39
  publication-title: WIREs Data Mining and Knowledge Discovery
  doi: 10.1002/widm.1312
– ident: 70_CR49
  doi: 10.1016/j.semcancer.2018.07.001.
– volume-title: Making Mathematical Culture: University and Print in the Circle of Lefèvre D’Étaples
  year: 2018
  ident: 70_CR65
  doi: 10.1093/oso/9780198823520.001.0001
– ident: 70_CR31
– ident: 70_CR7
  doi: 10.26225/FDZH-X261
– ident: 70_CR48
– ident: 70_CR18
  doi: 10.1093/llc/fqw045
– ident: 70_CR67
– ident: 70_CR81
  doi: 10.1007/978-3-030-28954-6
– ident: 70_CR94
  doi: 10.3390/jimaging7120260
– ident: 70_CR34
– ident: 70_CR70
– ident: 70_CR1
  doi: 10.18653/v1/D19-1668
– ident: 70_CR75
  doi: 10.1007/978-3-319-24574-4_28
– ident: 70_CR96
  doi: 10.1007/978-3-030-86334-0_8
– volume: 44
  start-page: 7581
  issue: 11
  year: 2022
  ident: 70_CR84
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2021.3115452
– ident: 70_CR11
– ident: 70_CR9
  doi: 10.1086/663607
– volume: 116
  start-page: 1
  issue: 1
  year: 2016
  ident: 70_CR43
  publication-title: International Journal of Computer Vision
  doi: 10.1007/s11263-015-0823-z
– ident: 70_CR90
– volume: 7
  start-page: 417
  issue: 1
  year: 2021
  ident: 70_CR41
  publication-title: Open Archaeology
  doi: 10.1515/opar-2020-0136
– ident: 70_CR62
  doi: 10.1109/BCI57258.2023.10078502
– volume: 1
  start-page: 236
  year: 2019
  ident: 70_CR99
  publication-title: Nature Machine Intelligence
  doi: 10.1038/s42256-019-0052-1
– ident: 70_CR29
  doi: 10.1007/s13222-022-00414-1
– ident: 70_CR17
  doi: 10.3390/jimaging8100285
– ident: 70_CR71
  doi: 10.1007/s13347-022-00558-8
– ident: 70_CR98
SSID ssj0002710283
Score 2.2405527
Snippet The recent advancements in the field of Artificial Intelligence (AI) translated to an increased adoption of AI technology in the humanities, which is often...
SourceID crossref
springer
SourceType Enrichment Source
Index Database
Publisher
StartPage 299
SubjectTerms Applied Statistics
Computational Linguistics
Cultural Studies
Digital/New Media
Mathematics and Statistics
Natural Language Processing (NLP)
Original Paper
Statistics
Title Explainability and transparency in the realm of digital humanities: toward a historian XAI
URI https://link.springer.com/article/10.1007/s42803-023-00070-1
Volume 5
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVQu3RBfIryUXlgA4s4ie2ara2oChKdqFSxRPEXVCopomHov-fspJWKUCX2c4bLxe8u9nsPoWsBmJQLJ4lRMKumThrSTXJNYu5o1yaKR8G15HnMR5P0acqmtUyO58L8Or-_W6bePokAsnj-s4gITDpNBhuvr-YBH2z-p8QVVNa8mL-XbmPP9sFnwJPhAdqvG0Hcq97cIdqzxRFq-d6vkk4-Rq_-flwgN_n7qysMMz8ugxa5J3DpFZ4VGNo3DG3f_AMvHDazN28Bgt8rUQuYge9xGa7F4hxXwsJQDHjaezxBk-HDy2BEaisEoilgCGE6ZjbSNBFMmpxppiHFNqHGUeUV413OrAQwj42kSjslHe9GhsVCp5aaPE5OUaNYFPYM4dRBi8qdTACXUhFxKZhRIoKoBB7CVRvRdZIyXeuEe7uKebZROA6JzSCxWUhsRtvoZrPms1LJ2Bl9u859Vn8xyx3h5_8Lv0Atbwlf8QUvUaP8-rZX0DiUqoOavWG_P-6EyvkBPua6Og
linkProvider Springer Nature
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8JAEN0YPMjF-Bnxcw_edGO37XZZb4RIQIETJMRL0_1SEixG6oF_7-y2kGAMiffZHqbbvDedmfcQuuWASRm3gmgJtWpshSbNKFMkTCxtmkgmgXctGQyT7jh-nrBJJZPjdmF-9e8fFrGzTyKALG7_mQcEKp1d17l0OvntpL3-nxKWUFntxfx9dBN7NhufHk86B2i_IoK4Vb65Q7Rj8iNUd9yvlE4-Rq9uPs4vN7n51SWGmh8XXovcLXCpJZ7mGOgbBto3-8Bzi_X0zVmA4PdS1AJq4Edc-LFYnOFSWBguA560eido3HkatbukskIgigKGEKZCZgJFI86EzphiClJsIqotlU4x3mbMCADzUAsqlZXCJs1As5Cr2FCdhdEpquXz3JwhHFugqIkVEeBSzINEcKYlDyAqgocksoHoKkmpqnTCnV3FLF0rHPvEppDY1Cc2pQ10tz7zWapkbI2-X-U-rb6YxZbw8_-F36C97mjQT_u94csFqjt7-HJ38BLViq9vcwUkopDX_vb8AEkFu60
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwGA0yQfYiXnFe8-CbhjVtky6-jenYvAwfHAxfSpuLDmY3tD7s3_sl6YYDGfj-pQ9fU85J851zELpMAJOyxAiicjirxkYo0ooySUJuaEtHOQ9casnTgPeG8f2IjX6p-N20--JK0msarEtTUTZnyjSXwrfYhioRwBurik4CAuefTevVZYf6Oryz_MsSegCt1DJ_L11FpNXrUIcy3R20XdFD3Pbvcxdt6GIP1S0j9IbK--jVTs05yZOdap3jrFC4dA7lVtYl53hcYCB1GMjg5ANPDVbjNxsMgt-91QWcjG9w6YZlcYa93TBsETxq9w_QsHv30umRKiCBSArIQpgMmQ4kjRImVMYkk9B4HVFlaG595E3GtACID5WguTS5MLwVKBYmMtZUZWF0iGrFtNBHCMcGiCs3IgK0ipOAi4SpPAmgKoKH8LyB6KJJqazcw22IxSRd-h67xqbQ2NQ1NqUNdLVcM_PeGWurrxe9T6vv6GtN-fH_yi_Q1vNtN33sDx5OUN1mxntB4SmqlZ_f-gyYRZmfu83zA0eow_0
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Explainability+and+transparency+in+the+realm+of+digital+humanities%3A+toward+a+historian+XAI&rft.jtitle=International+journal+of+digital+humanities&rft.au=El-Hajj%2C+Hassan&rft.au=Eberle%2C+Oliver&rft.au=Merklein%2C+Anika&rft.au=Siebold%2C+Anna&rft.date=2023-11-01&rft.issn=2524-7840&rft.eissn=2524-7840&rft.volume=5&rft.issue=2-3&rft.spage=299&rft.epage=331&rft_id=info:doi/10.1007%2Fs42803-023-00070-1&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s42803_023_00070_1
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2524-7840&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2524-7840&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2524-7840&client=summon