{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:13:35Z","timestamp":1743077615988,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031724367"},{"type":"electronic","value":"9783031724374"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72437-4_9","type":"book-chapter","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T20:41:19Z","timestamp":1727296879000},"page":"144-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LIT: Label-Informed Transformers on\u00a0Token-Based Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7857-8737","authenticated-orcid":false,"given":"Wenjun","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5993-1630","authenticated-orcid":false,"given":"Hanh Thi Hong","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-2990","authenticated-orcid":false,"given":"Carlos-Emiliano","family":"Gonz\u00e1lez-Gallardo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-439X","authenticated-orcid":false,"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-3356","authenticated-orcid":false,"given":"Antoine","family":"Doucet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"unstructured":"Almazrouei, E., et al.: The Falcon series of language models: towards open Frontier models (2023)","key":"9_CR1"},{"doi-asserted-by":"crossref","unstructured":"Boro\u015f, E., et al.: Alleviating digitization errors in named entity recognition for historical documents. In: Proceedings of the 24th Conference on Computational Natural Language Learning, pp. 431\u2013441 (2020)","key":"9_CR2","DOI":"10.18653\/v1\/2020.conll-1.35"},{"doi-asserted-by":"crossref","unstructured":"Crane, G., Jones, A.: The challenge of Virginia banks: an evaluation of named entity analysis in a 19th-century newspaper collection. In: Proceedings of the 6th ACM\/IEEE-Cs Joint Conference on Digital Libraries, pp. 31\u201340 (2006)","key":"9_CR3","DOI":"10.1145\/1141753.1141759"},{"issue":"2","key":"9_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3604931","volume":"56","author":"M Ehrmann","year":"2023","unstructured":"Ehrmann, M., Hamdi, A., Pontes, E.L., Romanello, M., Doucet, A.: Named entity recognition and classification in historical documents: a survey. ACM Comput. Surv. 56(2), 1\u201347 (2023)","journal-title":"ACM Comput. Surv."},{"unstructured":"Ehrmann, M., Romanello, M., Clematide, S., Str\u00f6bel, P., Barman, R.: Language resources for historical newspapers: the impresso collection (2020)","key":"9_CR5"},{"doi-asserted-by":"crossref","unstructured":"Ehrmann, M., Romanello, M., Fl\u00fcckiger, A., Clematide, S.: Extended overview of CLEF HIPE 2020: named entity processing on historical newspapers. In: CLEF 2020 Working Notes. Conference and Labs of the Evaluation Forum, vol.\u00a02696. CEUR-WS (2020)","key":"9_CR6","DOI":"10.1007\/978-3-030-58219-7_21"},{"doi-asserted-by":"crossref","unstructured":"Ehrmann, M., et al.: Extended overview of HIPE-2022: named entity recognition and linking in multilingual historical documents. In: CEUR Workshop Proceedings, pp. 1038\u20131063, No.\u00a03180, CEUR-WS (2022)","key":"9_CR7","DOI":"10.1007\/978-3-031-13643-6_26"},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi, L., Chiriatti, M.: GPT-3: its nature, scope, limits, and consequences. Mind. Mach. 30, 681\u2013694 (2020)","journal-title":"Mind. Mach."},{"doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Gallardo, C.E., Boros, E., Girdhar, N., Hamdi, A., Moreno, J.G., Doucet, A.: Yes but.. can chatGPT identify entities in historical documents? In: 2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp. 184\u2013189. IEEE (2023)","key":"9_CR9","DOI":"10.1109\/JCDL57899.2023.00034"},{"doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Gallardo, C.E., Tran, T.H.H., Girdhar, N., Boro\u015f, E., Moreno, J.G., Doucet, A.: L3i++ at SemEval-2023 task 2: prompting for multilingual complex named entity recognition. In: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval 2023), pp. 807\u2013814 (2023)","key":"9_CR10","DOI":"10.18653\/v1\/2023.semeval-1.112"},{"doi-asserted-by":"crossref","unstructured":"Hamdi, A., et al.: A multilingual dataset for named entity recognition, entity linking and stance detection in historical newspapers. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2328\u20132334 (2021)","key":"9_CR11","DOI":"10.1145\/3404835.3463255"},{"unstructured":"Hazem, A., Bouhandi, M., Boudin, F., Daille, B.: TermEval 2020: TALN-LS2N system for automatic term extraction. In: Proceedings of the 6th International Workshop on Computational Terminology, pp. 95\u2013100 (2020)","key":"9_CR12"},{"doi-asserted-by":"crossref","unstructured":"Iva\u010di\u010d, N., Tran, T.H.H., Koloski, B., Pollak, S., Purver, M.: Analysis of transfer learning for named entity recognition in south-Slavic languages. In: Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pp. 106\u2013112 (2023)","key":"9_CR13","DOI":"10.18653\/v1\/2023.bsnlp-1.13"},{"unstructured":"Karimi, A., Rossi, L., Prati, A.: Improving BERT performance for aspect-based sentiment analysis. arXiv preprint arXiv:2010.11731 (2020)","key":"9_CR14"},{"unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, vol.\u00a01, p.\u00a02 (2019)","key":"9_CR15"},{"doi-asserted-by":"crossref","unstructured":"Koufakou, A., Pamungkas, E.W., Basile, V., Patti, V., et\u00a0al.: HurtBERT: incorporating lexical features with BERT for the detection of abusive language. In: Proceedings of the Fourth Workshop on Online Abuse and Harms, pp. 34\u201343. Association for Computational Linguistics (2020)","key":"9_CR16","DOI":"10.18653\/v1\/2020.alw-1.5"},{"unstructured":"Labusch, K., Neudecker, C.: Entity linking in multilingual newspapers and classical commentaries with BERT (2022)","key":"9_CR17"},{"doi-asserted-by":"crossref","unstructured":"Lang, C., Wachowiak, L., Heinisch, B., Gromann, D.: Transforming term extraction: transformer-based approaches to multilingual term extraction across domains. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 3607\u20133620 (2021)","key":"9_CR18","DOI":"10.18653\/v1\/2021.findings-acl.316"},{"unstructured":"Li, Z., et al.: Label supervised llama finetuning. arXiv preprint arXiv:2310.01208 (2023)","key":"9_CR19"},{"doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: BertGCN: transductive text classification by combining GNN and BERT. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 1456\u20131462 (2021)","key":"9_CR20","DOI":"10.18653\/v1\/2021.findings-acl.126"},{"issue":"3","key":"9_CR21","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.3390\/app13031445","volume":"13","author":"J Mutinda","year":"2023","unstructured":"Mutinda, J., Mwangi, W., Okeyo, G.: Sentiment analysis of text reviews using lexicon-enhanced BERT embedding (LeBERT) model with convolutional neural network. Appl. Sci. 13(3), 1445 (2023)","journal-title":"Appl. Sci."},{"unstructured":"OpenAI: GPT-4 technical report (2023)","key":"9_CR22"},{"issue":"1","key":"9_CR23","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learning Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learning Res."},{"unstructured":"Rigouts\u00a0Terryn, A., Hoste, V., Drouin, P., Lefever, E.: TermEval 2020: shared task on automatic term extraction using the annotated corpora for term extraction research (ACTER) dataset. In: 6th International Workshop on Computational Terminology (COMPUTERM 2020), pp. 85\u201394. European Language Resources Association (ELRA) (2020)","key":"9_CR24"},{"issue":"2","key":"9_CR25","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s10579-019-09453-9","volume":"54","author":"A Rigouts Terryn","year":"2020","unstructured":"Rigouts Terryn, A., Hoste, V., Lefever, E.: In no uncertain terms: a dataset for monolingual and multilingual automatic term extraction from comparable corpora. Lang. Resour. Eval. 54(2), 385\u2013418 (2020)","journal-title":"Lang. Resour. Eval."},{"unstructured":"Ritze, D., Zirn, C., Greenstreet, C., Eckert, K., Ponzetto, S.P.: Named entities in court: the marinelives corpus. In: Language Resources and Technologies for Processing and Linking Historical Documents and Archives-Deploying Linked Open Data in Cultural Heritage\u2013LRT4HDA Workshop Programme, p.\u00a026 (2014)","key":"9_CR26"},{"unstructured":"Rosset, S., Grouin, C., Zweigenbaum, P.: Entit\u00e9s nomm\u00e9es structur\u00e9es: guide d\u2019annotation Quaero. LIMSI-Centre national de la recherche scientifique (2011)","key":"9_CR27"},{"unstructured":"Ryser, A., Nguyen, Q.A., Bodenmann, N., Chen, S.Y.: Exploring transformers for multilingual historical named entity recognition (2022)","key":"9_CR28"},{"unstructured":"Schweter, S., M\u00e4rz, L., Schmid, K., \u00c7ano, E.: hmBERT: historical multilingual language models for named entity recognition (2022)","key":"9_CR29"},{"unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)","key":"9_CR30"},{"key":"9_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/978-3-030-91669-5_21","volume-title":"Towards Open and Trustworthy Digital Societies","author":"TTH Hanh","year":"2021","unstructured":"Hanh, T.T.H., Doucet, A., Sidere, N., Moreno, J.G., Pollak, S.: Named entity recognition architecture combining contextual and global features. In: Ke, H.-R., Lee, C.S., Sugiyama, K. (eds.) ICADL 2021. LNCS, vol. 13133, pp. 264\u2013276. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-91669-5_21"},{"unstructured":"Tran, H.T.H., Martinc, M., Caporusso, J., Doucet, A., Pollak, S.: The recent advances in automatic term extraction: a survey. arXiv preprint arXiv:2301.06767 (2023)","key":"9_CR32"},{"key":"9_CR33","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/978-3-031-18840-4_26","volume-title":"DS 2022","author":"HTH Tran","year":"2022","unstructured":"Tran, H.T.H., Martinc, M., Doucet, A., Pollak, S.: Can cross-domain term extraction benefit from cross-lingual transfer? In: Pascal, P., Ienco, D. (eds.) DS 2022. LNCS, vol. 13601, pp. 363\u2013378. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18840-4_26"},{"key":"9_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1007\/978-3-031-21756-2_7","volume-title":"ICADL 2022","author":"HTH Tran","year":"2022","unstructured":"Tran, H.T.H., Martinc, M., Pelicon, A., Doucet, A., Pollak, S.: Ensembling transformers for cross-domain automatic term extraction. In: Tseng, Y.H., Katsurai, M., Nguyen, H.N. (eds.) ICADL 2022. LNCS, vol. 13636, pp. 90\u2013100. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-21756-2_7"},{"issue":"7","key":"9_CR35","doi-asserted-by":"publisher","first-page":"4285","DOI":"10.1007\/s10994-023-06506-7","volume":"113","author":"HTH Tran","year":"2024","unstructured":"Tran, H.T.H., Martinc, M., Repar, A., Ljube\u0161i\u0107, N., Doucet, A., Pollak, S.: Can cross-domain term extraction benefit from cross-lingual transfer and nested term labeling? Mach. Learn. 113(7), 4285\u20134314 (2024)","journal-title":"Mach. Learn."},{"unstructured":"Tran, H., Martinc, M., Doucet, A., Pollak, S.: A transformer-based sequence-labeling approach to the slovenian cross-domain automatic term extraction. In: Slovenian conference on Language Technologies and Digital Humanities (2022)","key":"9_CR36"},{"key":"9_CR37","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3389\/fdigh.2018.00002","volume":"5","author":"M Won","year":"2018","unstructured":"Won, M., Murrieta-Flores, P., Martins, B.: Ensemble named entity recognition (NER): evaluating NER tools in the identification of place names in historical corpora. Front. Digit. Humanit. 5, 2 (2018)","journal-title":"Front. Digit. Humanit."},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","key":"9_CR38","DOI":"10.1145\/3394486.3403172"},{"doi-asserted-by":"crossref","unstructured":"Yang, Y., Katiyar, A.: Simple and effective few-shot named entity recognition with structured nearest neighbor learning. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6365\u20136375 (2020)","key":"9_CR39","DOI":"10.18653\/v1\/2020.emnlp-main.516"},{"doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, H., Zhang, J., Ma, J., Chang, Y.: Attention-based multi-level feature fusion for named entity recognition. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 3594\u20133600 (2021)","key":"9_CR40","DOI":"10.24963\/ijcai.2020\/497"},{"unstructured":"Yao, L., Mao, C., Luo, Y.: KG-BERT: BERT for knowledge graph completion. arXiv preprint arXiv:1909.03193 (2019)","key":"9_CR41"},{"key":"9_CR42","doi-asserted-by":"publisher","first-page":"176600","DOI":"10.1109\/ACCESS.2019.2953990","volume":"7","author":"S Yu","year":"2019","unstructured":"Yu, S., Su, J., Luo, D.: Improving BERT-based text classification with auxiliary sentence and domain knowledge. IEEE Access 7, 176600\u2013176612 (2019)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: Ernie: enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129 (2019)","key":"9_CR43","DOI":"10.18653\/v1\/P19-1139"}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72437-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:03:22Z","timestamp":1731647002000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72437-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031724367","9783031724374"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72437-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare relevant to this article\u2019s content.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2024.nuk.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}