{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T19:49:28Z","timestamp":1772480968015,"version":"3.50.1"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T00:00:00Z","timestamp":1663286400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Comput. Cult. Herit."],"published-print":{"date-parts":[[2022,9,30]]},"abstract":"<jats:p>The amount of archaeological literature is growing rapidly. Until recently, these data were only accessible through metadata search. We implemented a text retrieval engine for a large archaeological text collection (~658 million words). In archaeological IR, domain-specific entities such as locations, time periods and artefacts play a central role. This motivated the development of a named entity recognition (NER) model to annotate the full collection with archaeological named entities. In this article, we present ArcheoBERTje, a BERT (Bidirectional Encoder Representations from Transformers) model pre-trained on Dutch archaeological texts. We compare the model\u2019s quality and output on an NER task to a generic multilingual model and a generic Dutch model. We also investigate ensemble methods for combining multiple BERT models, and combining the best BERT model with a domain thesaurus using conditional random fields. We find that ArcheoBERTje outperforms both the multilingual and Dutch model significantly with a smaller standard deviation between runs, reaching an average F1 score of 0.735. The model also outperforms ensemble methods combining the three models. Combining ArcheoBERTje predictions and explicit domain knowledge from the thesaurus did not increase the F1 score. We quantitatively and qualitatively analyse the differences between the vocabulary and output of the BERT models on the full collection and provide some valuable insights in the effect of fine-tuning for specific domains. Our results indicate that for a highly specific text domain such as archaeology, further pre-training on domain-specific data increases the model\u2019s quality on NER by a much larger margin than shown for other domains in the literature, and that domain-specific pre-training makes the addition of domain knowledge from a thesaurus unnecessary.<\/jats:p>","DOI":"10.1145\/3497842","type":"journal-article","created":{"date-parts":[[2022,2,18]],"date-time":"2022-02-18T20:26:37Z","timestamp":1645215997000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":47,"title":["Can BERT Dig It? Named Entity Recognition for Information Retrieval in the Archaeology Domain"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1623-1340","authenticated-orcid":false,"given":"Alex","family":"Brandsen","sequence":"first","affiliation":[{"name":"Leiden University, Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suzan","family":"Verberne","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karsten","family":"Lambers","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milco","family":"Wansleeben","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4010"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.23919\/FRUCT48808.2020.9087359"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTTA.2008.4529905"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1371"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4739063"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.5334\/jcaa.33"},{"key":"e_1_3_2_8_2","first-page":"4573","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Brandsen Alex","year":"2020","unstructured":"Alex Brandsen, Suzan Verberne, Milco Wansleeben, and Karsten Lambers. 2020. Creating a dataset for named entity recognition in the archaeology domain. In Proceedings of the 12th Language Resources and Evaluation Conference. 4573\u20134577."},{"key":"e_1_3_2_9_2","volume-title":"Archeologisch Basisregister","author":"Brandt R. W.","year":"1992","unstructured":"R. W. Brandt, E. Drenth, M. Montforts, R. H. P. Proos, I. M. Roorda, and R. Wiemer. 1992. Archeologisch Basisregister. Technical Report. Rijksdienst voor Cultureel Erfgoed, Amersfoort."},{"key":"e_1_3_2_10_2","first-page":"48","volume-title":"Making History Interactive: Computer Applications and Quantitative Methods in Archaeology 2009","author":"Byrne Kate","year":"2010","unstructured":"Kate Byrne and Ewan Klein. 2010. Automatic extraction of archaeological events from text. In Making History Interactive: Computer Applications and Quantitative Methods in Archaeology 2009, B. Frischer, J. Crawford, and D. Koller (Eds.). BAR International Series 2079, Oxford, 48\u201356."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.14778\/1988776.1988781"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2071389.2071390"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.598"},{"key":"e_1_3_2_14_2","unstructured":"Xiang Cheng Mitchell Bowden Bhushan Ramesh Bhange Priyanka Goyal Thomas Packer and Faizan Javed. 2020. An end-to-end solution for named entity recognition in eCommerce search. arXiv:2012.07553 (2020). http:\/\/arxiv.org\/abs\/2012.07553."},{"key":"e_1_3_2_15_2","unstructured":"Jenny Copara Nona Naderi Julien Knafou Patrick Ruch and Douglas Teodoro. 2020. Named entity recognition in chemical patents using ensemble of contextual language models. arXiv:2007.12569 (2020). http:\/\/arxiv.org\/abs\/2007.12569."},{"key":"e_1_3_2_16_2","volume-title":"Opperlandse Taal- & Letterkunde","author":"Corstius Hugo Brandt","year":"1981","unstructured":"Hugo Brandt Corstius. 1981. Opperlandse Taal- & Letterkunde. Querido."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i2.19050"},{"key":"e_1_3_2_18_2","unstructured":"Wietse de Vries Andreas van Cranenburgh Arianna Bisazza Tommaso Caselli Gertjan van Noord and Malvina Nissim. 2019. BERTje: A Dutch BERT Model. arXiv:1912.09582 (2019). http:\/\/arxiv.org\/abs\/1912.09582."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.292"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_21_2","unstructured":"ElasticSearch. 2018. Theory Behind Relevance Scoring. Retrieved February 24 2022 from https:\/\/www.elastic.co\/guide\/en\/elasticsearch\/guide\/current\/scoring-theory.html."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1080\/03122417.2012.11681957"},{"key":"e_1_3_2_23_2","volume-title":"Elasticsearch: The Definitive Guide: A Distributed Real-Time Search and Analytics Engine","author":"Gormley C.","year":"2015","unstructured":"C. Gormley and Z. Tong. 2015. Elasticsearch: The Definitive Guide: A Distributed Real-Time Search and Analytics Engine. O\u2019Reilly Media, Sebastopol."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1571989"},{"key":"e_1_3_2_25_2","volume-title":"Over Zaaien En Oogsten, De Kwaliteit En Bruikbaarheid Van Archeologische Rapporten Voor Synthetiserend Onderzoek","author":"Habermehl Diederick","year":"2019","unstructured":"Diederick Habermehl. 2019. Over Zaaien En Oogsten, De Kwaliteit En Bruikbaarheid Van Archeologische Rapporten Voor Synthetiserend Onderzoek. Technical Report. Rijksdienst voor Cultureel Erfgoed, Amersfoort. https:\/\/www.cultureelerfgoed.nl\/publicaties\/publicaties\/2019\/01\/01\/over-zaaien-en-oogsten."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-5709"},{"key":"e_1_3_2_27_2","unstructured":"M. Honnibal and I. Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings convolutional neural networks and incremental parsing. To appear."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2009.0038"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01241-8"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"e_1_3_2_31_2","unstructured":"Yuri Kuratov and Mikhail Arkhipov. 2019. Adaptation of deep bidirectional multilingual transformers for Russian language. arXiv:1905.07213 (2019). http:\/\/arxiv.org\/abs\/1905.07213."},{"key":"e_1_3_2_32_2","first-page":"282","volume-title":"Proceedings of the 18th International Conference on Machine Learning","author":"Lafferty John","year":"2001","unstructured":"John Lafferty, Andrew Mccallum, Fernando C. N. Pereira, and Fernando Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the 18th International Conference on Machine Learning. 282\u2013289."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103422"},{"key":"e_1_3_2_35_2","volume-title":"Proceedings of the 1st International Conference on Learning Representations (ICLR\u201913)\u2014Workshop Track Proceedings","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In Proceedings of the 1st International Conference on Learning Representations (ICLR\u201913)\u2014Workshop Track Proceedings."},{"key":"e_1_3_2_36_2","unstructured":"Taesun Moon Parul Awasthy Jian Ni and Radu Florian. 2019. Towards lingua franca named entity recognition with BERT. arXiv:1912.01389 (2019). http:\/\/arxiv.org\/abs\/1912.01389."},{"key":"e_1_3_2_37_2","unstructured":"Peter Norvig. 2013. English Letter Frequency Counts: Mayzner Revisited. Retrieved February 24 2022 from http:\/\/norvig.com\/mayzner.html."},{"key":"e_1_3_2_38_2","unstructured":"Debora Nozza Federico Bianchi and Dirk Hovy. 2020. What the [MASK]? Making sense of language-specific BERT models. arXiv:2003.02912 (2020). http:\/\/arxiv.org\/abs\/2003.02912."},{"key":"e_1_3_2_39_2","first-page":"2","volume-title":"Proceedings of the 18th Annual Belgian-Dutch Conference on Machine Learning (Benelearn)","author":"Paijmans Hans","year":"2009","unstructured":"Hans Paijmans and Alex Brandsen. 2009. What is in a name: Recognizing monument names from free-text monument descriptions. In Proceedings of the 18th Annual Belgian-Dutch Conference on Machine Learning (Benelearn), M. G. J. van Erp, J. H. Stehouwer, and M. van Zaanen (Eds.). Tilburg Centre for Creative Computing, Tilburg, 2\u20136."},{"issue":"2","key":"e_1_3_2_40_2","first-page":"1","article-title":"Searching in archaeological texts: Problems and solutions using an artificial intelligence approach","volume":"7","author":"Paijmans H.","year":"2010","unstructured":"H. Paijmans and A. Brandsen. 2010. Searching in archaeological texts: Problems and solutions using an artificial intelligence approach. PalArch\u2019s Journal of Archaeology of Egypt\/Egyptology 7, 2 (2010), 1\u20136.","journal-title":"PalArch\u2019s Journal of Archaeology of Egypt\/Egyptology"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2041-5370.2016.12037.x"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/caia.1991.120841"},{"key":"e_1_3_2_43_2","unstructured":"RCE. 2017. De Erfgoedmonitor. Retrieved February 24 2022 from https:\/\/erfgoedmonitor.cultureelerfgoed.nl\/mosaic\/kerncijfers\/."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1201\/b18530-15"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.14257\/ijseia.2016.10.2.08"},{"key":"e_1_3_2_46_2","first-page":"239","volume-title":"Proceedings of the 20th Nordic Conference of Computational Linguistics (NODALIDA\u201915)","author":"Sien\u010dnik Scharolta Katharina","year":"2015","unstructured":"Scharolta Katharina Sien\u010dnik. 2015. Adapting word2vec to named entity recognition. In Proceedings of the 20th Nordic Conference of Computational Linguistics (NODALIDA\u201915). 239\u2013243."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010025"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76973-6_12"},{"key":"e_1_3_2_49_2","unstructured":"F\u00e1bio Souza Rodrigo Nogueira and Roberto Lotufo. 2019. Portuguese named entity recognition using BERT-CRF. arXiv:1909.10649 (2019). http:\/\/arxiv.org\/abs\/1909.10649."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1355"},{"key":"e_1_3_2_51_2","volume-title":"Improving the Discoverability of Zooarchaeological Data with the Help of Natural Language Processing.","author":"Talboom Leontien","year":"2017","unstructured":"Leontien Talboom. 2017. Improving the Discoverability of Zooarchaeological Data with the Help of Natural Language Processing.Ph.D. Dissertation. University of York."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51310-8_2"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.2200\/s00190ed1v01y200904icr005"},{"key":"e_1_3_2_54_2","first-page":"126","volume-title":"When Valletta Meets Faro, the Reality of European Archaeology in the 21st Century, Proceedings of the International Conference","author":"Dries Monique Van den","year":"2016","unstructured":"Monique Van den Dries. 2016. Is everybody happy? User satisfaction after ten years of quality management in European archaeological heritage management. In When Valletta Meets Faro, the Reality of European Archaeology in the 21st Century, Proceedings of the International Conference, P. Florjanowicz (Ed.). Archaeolingua, Lisbon, 126\u2013135."},{"key":"e_1_3_2_55_2","unstructured":"Antti Virtanen Jenna Kanerva Rami Ilo Jouni Luoma Juhani Luotolahti Tapio Salakoski Filip Ginter and Sampo Pyysalo. 2019. Multilingual is not enough: BERT for Finnish. arXiv:1912.07076 (2019). http:\/\/arxiv.org\/abs\/1912.07076."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34399-5_10"},{"key":"e_1_3_2_57_2","volume-title":"D16.4: Final Report on Natural Language Processing","author":"Vlachidis A.","year":"2017","unstructured":"A. Vlachidis, D. Tudhope, M. Wansleeben, J. Azzopardi, K. Green, L. Xia, and H. Wright. 2017. D16.4: Final Report on Natural Language Processing. Technical Report. ARIADNE. http:\/\/legacy.ariadne-infrastructure.eu\/wp-content\/uploads\/2019\/01\/D16.4_Final_Report_on_Natural_Language_Processing_Final.pdf."},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3365109.3368765"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.16"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.523"}],"container-title":["Journal on Computing and Cultural Heritage"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3497842","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3497842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:04Z","timestamp":1750188604000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3497842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,16]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,9,30]]}},"alternative-id":["10.1145\/3497842"],"URL":"https:\/\/doi.org\/10.1145\/3497842","relation":{},"ISSN":["1556-4673","1556-4711"],"issn-type":[{"value":"1556-4673","type":"print"},{"value":"1556-4711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,16]]},"assertion":[{"value":"2021-06-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}