{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:37:41Z","timestamp":1781476661883,"version":"3.54.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030865221","type":"print"},{"value":"9783030865238","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86523-8_41","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T06:05:16Z","timestamp":1631253916000},"page":"677-693","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Transformers: \u201cThe End of History\u201d for Natural Language Processing?"],"prefix":"10.1007","author":[{"given":"Anton","family":"Chernyavskiy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Ilvovsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Preslav","family":"Nakov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,11]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Arkhipov, M., Trofimova, M., Kuratov, Y., Sorokin, A.: Tuning multilingual transformers for language-specific named entity recognition. In: Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing (BSNLP 2019), pp. 89\u201393. Florence, Italy (2019)","DOI":"10.18653\/v1\/W19-3712"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Augenstein, I., Das, M., Riedel, S., Vikraman, L., McCallum, A.: SemEval 2017 task 10: ScienceIE - extracting keyphrases and relations from scientific publications. In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval 2017), pp. 546\u2013555. Vancouver, Canada (2017)","DOI":"10.18653\/v1\/S17-2091"},{"key":"41_CR3","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. In: ArXiv (2020)"},{"key":"41_CR4","unstructured":"Choromanski, K., et al.: Rethinking attention with performers. In: Proceedings of the 9th International Conference on Learning Representations (ICLR 2021) (2021)"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., Manning, C.D.: What does BERT look at? An analysis of BERT\u2019s attention, ArXiv (2019)","DOI":"10.18653\/v1\/W19-4828"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Da San Martino, G., Barr\u00f3n-Cede\u00f1o, A., Wachsmuth, H., Petrov, R., Nakov, P.: SemEval-2020 task 11: detection of propaganda techniques in news articles. In: Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval 2020), Barcelona, Spain (2020)","DOI":"10.18653\/v1\/2020.semeval-1.186"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Da San Martino, G., Yu, S., Barr\u00f3n-Cede\u00f1o, A., Petrov, R., Nakov, P.: Fine-grained analysis of propaganda in news article. 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 2019), pp. 5636\u20135646. Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1565"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., Salakhutdinov, R.: TransformerXL: attentive language models beyond a fixed-length context. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp. 2978\u20132988. Florence, Italy (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"41_CR9","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 (NAACL-HLT 2019), pp. 4171\u20134186. Minneapolis, MN, USA (2019)"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Durrani, N., Dalvi, F., Sajjad, H., Belinkov, Y., Nakov, P.: One size does not fit all: Comparing NMT representations of different granularities. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), pp. 1504\u20131516. Minneapolis, MN, USA (2019)","DOI":"10.18653\/v1\/N19-1154"},{"key":"41_CR11","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1162\/tacl_a_00298","volume":"8","author":"A Ettinger","year":"2020","unstructured":"Ettinger, A.: What BERT is not: lessons from a new suite of psycholinguistic diagnostics for language models. Trans. Assoc. Comput. Linguist. 8, 34\u201348 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"41_CR12","unstructured":"Goldberg, Y.: Assessing bert\u2019s syntactic abilities (2019)"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Jawahar, G., Sagot, B., Seddah, D.: What does BERT learn about the structure of language? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp. 3651\u20133657. Florence, Italy (2019)","DOI":"10.18653\/v1\/P19-1356"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Jin, D., Jin, Z., Zhou, J.T., Szolovits, P.: Is BERT really robust? a strong baseline for natural language attack on text classification and entailment. In: Proceedings of the 34th Conference on Artificial Intelligence (AAAI 2020), pp. 8018\u20138025 (2019)","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"41_CR15","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: Proceedings of the 37th International Conference on Machine Learning (ICML 2020), pp. 5156\u20135165 (2020)"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Kovaleva, O., Romanov, A., Rogers, A., Rumshisky, A.: Revealing the dark secrets of BERT. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019), pp. 4365\u20134374. Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1445"},{"key":"41_CR17","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), pp. 282\u2013289. Williamstown, MA, USA (2001)"},{"key":"41_CR18","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: ArXiv (2019)"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Liu, N.F., Gardner, M., Belinkov, Y., Peters, M.E., Smith, N.A.: Linguistic knowledge and transferability of contextual representations. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), pp. 1073\u20131094. Minneapolis, MN, USA (2019)","DOI":"10.18653\/v1\/N19-1112"},{"key":"41_CR20","unstructured":"Liu, Y., et al.: RoBERTa: A robustly optimized BERT pretraining approach. In: ArXiv (2019)"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Peters, M., 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 (NAACL-HLT 2018), pp. 2227\u20132237. New Orleans, LA, USA (2018)","DOI":"10.18653\/v1\/N18-1202"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Knowledge enhanced contextual word representations. 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 2019), pp. 43\u201354. Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1005"},{"issue":"1","key":"41_CR23","doi-asserted-by":"publisher","first-page":"43","DOI":"10.2478\/pralin-2018-0002","volume":"110","author":"M Popel","year":"2018","unstructured":"Popel, M., Bojar, O.: Training tips for the transformer model. Prague Bull. Math. Linguist. 110(1), 43\u201370 (2018)","journal-title":"Prague Bull. Math. Linguist."},{"issue":"3","key":"41_CR24","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"MF Porter","year":"1980","unstructured":"Porter, M.F.: An algorithm for suffix stripping. Program 14(3), 130\u2013137 (1980)","journal-title":"Program"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Ratinov, L.A., Roth, D.: Design challenges and misconceptions in named entity recognition. In: Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009), pp. 147\u2013155. Boulder, CO, USA (2009)","DOI":"10.3115\/1596374.1596399"},{"key":"41_CR26","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1162\/tacl_a_00349","volume":"8","author":"A Rogers","year":"2020","unstructured":"Rogers, A., Kovaleva, O., Rumshisky, A.: A primer in BERTology: what we know about how BERT works. Trans. Assoc. Comput. Linguist. 8, 842\u2013866 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"41_CR27","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In: ArXiv (2019)"},{"key":"41_CR28","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: Portuguese named entity recognition using BERT-CRF. In: Arxiv (2019)"},{"key":"41_CR29","unstructured":"Sun, L., et al.: Adv-BERT: BERT is not robust on misspellings! generating nature adversarial samples on BERT. In: Arxiv (2020)"},{"key":"41_CR30","unstructured":"Tenney, I., et al.: What do you learn from context? Probing for sentence structure in contextualized word representations. In: Arxiv (2019)"},{"key":"41_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Arxiv (2017)"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Wallace, E., Wang, Y., Li, S., Singh, S., Gardner, M.: Do NLP models know numbers? probing numeracy in embeddings. 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 2019), pp. 5307\u20135315. Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1534"},{"key":"41_CR33","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. In: Arxiv (2020)"},{"key":"41_CR34","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS 2019), pp. 5753\u20135763 (2019)"},{"key":"41_CR35","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS 2020) (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86523-8_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:04:57Z","timestamp":1757455497000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86523-8_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865221","9783030865238"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86523-8_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"11 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"869","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":"210","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":"24% - 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":"3-4","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":"3-9","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}