{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:26:25Z","timestamp":1771611985702,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031399640","type":"print"},{"value":"9783031399657","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-39965-7_49","type":"book-chapter","created":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T16:01:37Z","timestamp":1692547297000},"page":"593-606","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An Information Extraction Study: Take in\u00a0Mind the\u00a0Tokenization!"],"prefix":"10.1007","author":[{"given":"Christos","family":"Theodoropoulos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie-Francine","family":"Moens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,21]]},"reference":[{"key":"49_CR1","doi-asserted-by":"publisher","unstructured":"\u00c1cs, J., K\u00e1d\u00e1r, \u00c1., Kornai, A.: Subword pooling makes a difference. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 2284\u20132295. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.194, https:\/\/aclanthology.org\/2021.eacl-main.194","DOI":"10.18653\/v1\/2021.eacl-main.194"},{"key":"49_CR2","doi-asserted-by":"publisher","unstructured":"Alsentzer, E., et al.: Publicly available clinical BERT embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp. 72\u201378. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/W19-1909, https:\/\/aclanthology.org\/W19-1909","DOI":"10.18653\/v1\/W19-1909"},{"key":"49_CR3","unstructured":"Antoun, W., Baly, F., Hajj, H.: AraBERT: transformer-based model for Arabic language understanding. In: Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pp. 9\u201315. European Language Resource Association, Marseille (2020). https:\/\/aclanthology.org\/2020.osact-1.2"},{"key":"49_CR4","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.eswa.2018.07.032","volume":"114","author":"G Bekoulis","year":"2018","unstructured":"Bekoulis, G., Deleu, J., Demeester, T., Develder, C.: Joint entity recognition and relation extraction as a multi-head selection problem. Expert Syst. Appl. 114, 34\u201345 (2018). https:\/\/doi.org\/10.1016\/j.eswa.2018.07.032","journal-title":"Expert Syst. Appl."},{"key":"49_CR5","doi-asserted-by":"crossref","unstructured":"Clark, J.H., Garrette, D., Turc, I., Wieting, J.: CANINE: pre-training an efficient tokenization-free encoder for language representation. arXiv preprint arXiv:2103.06874 (2021)","DOI":"10.1162\/tacl_a_00448"},{"key":"49_CR6","doi-asserted-by":"crossref","unstructured":"Clark, J.H., Garrette, D., Turc, I., Wieting, J.: CANINE: pre-training an efficient tokenization-free encoder for language representation. Trans. Assoc. Comput. Linguist. 10, 73\u201391 (2022). https:\/\/aclanthology.org\/2022.tacl-1.5","DOI":"10.1162\/tacl_a_00448"},{"key":"49_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"49_CR8","doi-asserted-by":"publisher","unstructured":"Eberts, M., Ulges, A.: Span-based joint entity and relation extraction with transformer pre-training. In: ECAI 2020, pp. 2006\u20132013. IOS Press (2020). https:\/\/doi.org\/10.3233\/FAIA200321","DOI":"10.3233\/FAIA200321"},{"key":"49_CR9","doi-asserted-by":"publisher","unstructured":"El Boukkouri, H., Ferret, O., Lavergne, T., Noji, H., Zweigenbaum, P., Tsujii, J.: CharacterBERT: reconciling ELMo and BERT for word-level open-vocabulary representations from characters. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 6903\u20136915. International Committee on Computational Linguistics, Barcelona (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.609, https:\/\/aclanthology.org\/2020.coling-main.609","DOI":"10.18653\/v1\/2020.coling-main.609"},{"key":"49_CR10","unstructured":"Florian, R., Pitrelli, J., Roukos, S., Zitouni, I.: Improving mention detection robustness to noisy input. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 335\u2013345. Association for Computational Linguistics, Cambridge (2010). https:\/\/aclanthology.org\/D10-1033"},{"issue":"5","key":"49_CR11","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1016\/j.jbi.2012.04.008","volume":"45","author":"H Gurulingappa","year":"2012","unstructured":"Gurulingappa, H., Rajput, A.M., Roberts, A., Fluck, J., Hofmann-Apitius, M., Toldo, L.: Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports. J. Biomed. Inform. 45(5), 885\u2013892 (2012). https:\/\/doi.org\/10.1016\/j.jbi.2012.04.008","journal-title":"J. Biomed. Inform."},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Itzhak, I., Levy, O.: Models in a spelling bee: language models implicitly learn the character composition of tokens. arXiv preprint arXiv:2108.11193 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.373"},{"issue":"1","key":"49_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 1\u20139 (2016). https:\/\/doi.org\/10.1038\/sdata.2016.35","journal-title":"Sci. Data"},{"key":"49_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"49_CR15","doi-asserted-by":"publisher","unstructured":"Kudo, T., Richardson, J.: Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66\u201371. Association for Computational Linguistics, Brussels (2018). https:\/\/doi.org\/10.18653\/v1\/D18-2012, https:\/\/aclanthology.org\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"49_CR16","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: AlBERT: a lite BERT for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"issue":"4","key":"49_CR17","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinform. (Oxford Engl.) 36(4), 1234\u20131240 (2020). https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinform. (Oxford Engl.)"},{"issue":"1","key":"49_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-017-1609-9","volume":"18","author":"F Li","year":"2017","unstructured":"Li, F., Zhang, M., Fu, G., Ji, D.: A neural joint model for entity and relation extraction from biomedical text. BMC Bioinform. 18(1), 1\u201311 (2017). https:\/\/doi.org\/10.1186\/s12859-017-1609-9","journal-title":"BMC Bioinform."},{"key":"49_CR19","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"49_CR20","unstructured":"Mitchell, T.M.: The need for biases in learning generalizations. Department of Computer Science, Laboratory for Computer Science Research, Rutgers Univ. (1980)"},{"issue":"1","key":"49_CR21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1075\/li.30.1.03nad","volume":"30","author":"D Nadeau","year":"2007","unstructured":"Nadeau, D., Sekine, S.: A survey of named entity recognition and classification. Lingvisticae Invest. 30(1), 3\u201326 (2007). https:\/\/doi.org\/10.1075\/li.30.1.03nad","journal-title":"Lingvisticae Invest."},{"key":"49_CR22","doi-asserted-by":"publisher","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227\u20132237. Association for Computational Linguistics, New Orleans (2018). https:\/\/doi.org\/10.18653\/v1\/N18-1202, https:\/\/aclanthology.org\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"49_CR23","unstructured":"Plank, B., Moschitti, A.: Embedding semantic similarity in tree kernels for domain adaptation of relation extraction. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1498\u20131507. Association for Computational Linguistics, Sofia (2013). https:\/\/aclanthology.org\/P13-1147"},{"issue":"8","key":"49_CR24","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"issue":"6088","key":"49_CR25","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986). https:\/\/doi.org\/10.1038\/323533a0","journal-title":"Nature"},{"key":"49_CR26","doi-asserted-by":"publisher","unstructured":"Sasaki, S., Sun, S., Schamoni, S., Duh, K., Inui, K.: Cross-lingual learning-to-rank with shared representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 458\u2013463. Association for Computational Linguistics, New Orleans (2018). https:\/\/doi.org\/10.18653\/v1\/N18-2073, https:\/\/aclanthology.org\/N18-2073","DOI":"10.18653\/v1\/N18-2073"},{"key":"49_CR27","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715\u20131725. Association for Computational Linguistics, Berlin (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1162, https:\/\/aclanthology.org\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"49_CR28","unstructured":"Sun, A., Grishman, R., Sekine, S.: Semi-supervised relation extraction with large-scale word clustering. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 521\u2013529. Association for Computational Linguistics, Portland (2011). https:\/\/aclanthology.org\/P11-1053"},{"key":"49_CR29","doi-asserted-by":"crossref","unstructured":"Taill\u00e9, B., Guigue, V., Scoutheeten, G., Gallinari, P.: Let\u2019s stop error propagation in the end-to-end relation extraction literature! In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), pp. 3689\u20133701. Association for Computational Linguistics, Online (2020). https:\/\/www.aclweb.org\/anthology\/2020.emnlp-main.301.pdf","DOI":"10.18653\/v1\/2020.emnlp-main.301"},{"key":"49_CR30","unstructured":"Tay, Y., et al.: CharFormer: fast character transformers via gradient-based subword tokenization. arXiv preprint arXiv:2106.12672 (2021)"},{"key":"49_CR31","doi-asserted-by":"publisher","unstructured":"Theodoropoulos, C., Henderson, J., Coman, A.C., Moens, M.F.: Imposing relation structure in language-model embeddings using contrastive learning. In: Proceedings of the 25th Conference on Computational Natural Language Learning, pp. 337\u2013348. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.conll-1.27, https:\/\/aclanthology.org\/2021.conll-1.27","DOI":"10.18653\/v1\/2021.conll-1.27"},{"key":"49_CR32","unstructured":"Tiedemann, J., Thottingal, S., et al.: OPUS-MT-building open translation services for the world. In: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation (2020). https:\/\/aclanthology.org\/2020.eamt-1.61"},{"key":"49_CR33","doi-asserted-by":"publisher","unstructured":"Wang, J., Lu, W.: Two are better than one: joint entity and relation extraction with table-sequence encoders. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1706\u20131721. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.133, https:\/\/aclanthology.org\/2020.emnlp-main.133","DOI":"10.18653\/v1\/2020.emnlp-main.133"},{"key":"49_CR34","doi-asserted-by":"publisher","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6, https:\/\/aclanthology.org\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"49_CR35","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)"},{"key":"49_CR36","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: ByT5: towards a token-free future with pre-trained byte-to-byte models. Trans. Assoc. Comput. Linguist. 10, 291\u2013306 (2022). https:\/\/aclanthology.org\/2022.tacl-1.17","DOI":"10.1162\/tacl_a_00461"},{"key":"49_CR37","doi-asserted-by":"publisher","unstructured":"Yan, Z., Zhang, C., Fu, J., Zhang, Q., Wei, Z.: A partition filter network for joint entity and relation extraction. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 185\u2013197. Association for Computational Linguistics, Online and Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.17, https:\/\/aclanthology.org\/2021.emnlp-main.17","DOI":"10.18653\/v1\/2021.emnlp-main.17"},{"key":"49_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, H., Tan, L.: Textual representations for crosslingual information retrieval. In: Proceedings of The 4th Workshop on e-Commerce and NLP, pp. 116\u2013122 (2021). https:\/\/aclanthology.org\/2021.ecnlp-1.14.pdf","DOI":"10.18653\/v1\/2021.ecnlp-1.14"},{"key":"49_CR39","doi-asserted-by":"publisher","unstructured":"Zhao, S., Hu, M., Cai, Z., Liu, F.: Modeling dense cross-modal interactions for joint entity-relation extraction. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 4032\u20134038. International Joint Conferences on Artificial Intelligence Organization, Online (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/558","DOI":"10.24963\/ijcai.2020\/558"}],"container-title":["Lecture Notes in Computer Science","Fuzzy Logic and Technology, and Aggregation Operators"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39965-7_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T16:05:15Z","timestamp":1692547515000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39965-7_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031399640","9783031399657"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39965-7_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"21 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EUSFLAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Conference of the European Society for Fuzzy Logic and Technology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Palma de Mallorca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eusflat2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.eusflat2023.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"161","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"71","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}