{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T14:09:22Z","timestamp":1762092562772,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408366"},{"type":"electronic","value":"9783031408373"}],"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\/978-3-031-40837-3_18","type":"book-chapter","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T23:02:25Z","timestamp":1692658945000},"page":"301-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Fine-Tuning Language Models for\u00a0Scientific Writing Support"],"prefix":"10.1007","author":[{"given":"Justin","family":"M\u00fccke","sequence":"first","affiliation":[]},{"given":"Daria","family":"Waldow","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5202-507X","authenticated-orcid":false,"given":"Luise","family":"Metzger","sequence":"additional","affiliation":[]},{"given":"Philipp","family":"Schauz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8061-9396","authenticated-orcid":false,"given":"Marcel","family":"Hoffman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-6480","authenticated-orcid":false,"given":"Nicolas","family":"Lell","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2653-9245","authenticated-orcid":false,"given":"Ansgar","family":"Scherp","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,22]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Beltagy, I., Lo, K., Cohan, A.: Scibert: a pretrained language model for scientific text. In: Proceedings of EMNLP-IJCNLP 2019. ACL (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1371","DOI":"10.18653\/v1\/D19-1371"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bottomley, J.: Academic Writing for International Students of Science. Routledge, Abingdon (2022)","DOI":"10.4324\/9781003118572"},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Cao, Y., Wan, X.: DivGAN: towards diverse paraphrase generation via diversified generative adversarial network. In: Findings of the Association for Computational Linguistics: EMNLP 2020. ACL (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.218","DOI":"10.18653\/v1\/2020.findings-emnlp.218"},{"key":"18_CR4","unstructured":"Carlini, N., et al.: Extracting training data from large language models. In: Bailey, M., Greenstadt, R. (eds.) 30th USENIX Security Symposium, USENIX Security 2021(August), pp. 11\u201313, 2021. pp. 2633\u20132650. USENIX Association (2021). https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/carlini-extracting"},{"key":"18_CR5","unstructured":"Clark, K., Luong, M., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generators. In: ICLR 2020. OpenReview.net (2020)"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Dabre, R., Chu, C., Kunchukuttan, A.: A survey of multilingual neural machine translation. ACM Comput. Surv. 53(5): 1\u201338 (2020). Article No. 99. https:\/\/doi.org\/10.1145\/3406095","DOI":"10.1145\/3406095"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019. ACL (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Diera, A., Lell, N., Garifullina, A., Scherp, A.: A study on extracting named entities from fine-tuned vs. differentially private fine-tuned BERT models. CoRR abs\/2212.03749 (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.03749","DOI":"10.48550\/arXiv.2212.03749"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Galke, L., et al.: Are we really making much progress? bag-of-words vs. sequence vs. graph vs. hierarchy for single- and multi-label text classification. CoRR (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.03954","DOI":"10.48550\/arXiv.2204.03954"},{"key":"18_CR10","doi-asserted-by":"publisher","unstructured":"Galke, L., Scherp, A.: Bag-of-words vs. graph vs. sequence in text classification: questioning the necessity of text-graphs and the surprising strength of a wide MLP. In: ACL 2022. ACL (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.279","DOI":"10.18653\/v1\/2022.acl-long.279"},{"key":"18_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-030-72113-8_11","volume-title":"Advances in Information Retrieval","author":"A Garcia-Silva","year":"2021","unstructured":"Garcia-Silva, A., Gomez-Perez, J.M.: Classifying scientific publications with BERT - is self-attention a feature selection method? In: Hiemstra, D., Moens, M.-F., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds.) ECIR 2021. LNCS, vol. 12656, pp. 161\u2013175. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72113-8_11"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-3-030-99736-6_19","volume-title":"Advances in Information Retrieval","author":"N Gu","year":"2022","unstructured":"Gu, N., Gao, Y., Hahnloser, R.H.R.: Local citation recommendation with hierarchical-attention text encoder and SciBERT-based reranking. In: Hagen, M., et al. (eds.) ECIR 2022. LNCS, vol. 13185, pp. 274\u2013288. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-99736-6_19"},{"key":"18_CR13","unstructured":"Gupta, A., Agarwal, A., Singh, P., Rai, P.: A deep generative framework for paraphrase generation. In: McIlraith, S.A., Weinberger, K.Q. (eds.) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2\u20137 February 2018, pp. 5149\u20135156. AAAI Press (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16353"},{"key":"18_CR14","unstructured":"Hegde, C.V., Patil, S.: Unsupervised paraphrase generation using pre-trained language models. CoRR (2020)"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Hu, Z., Lee, R.K., Aggarwal, C.C., Zhang, A.: Text style transfer: a review and experimental evaluation. SIGKDD Explor. (2022). https:\/\/doi.org\/10.1145\/3544903.3544906","DOI":"10.1145\/3544903.3544906"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"Jin, D., Jin, Z., Hu, Z., Vechtomova, O., Mihalcea, R.: Deep learning for text style transfer: a survey. COLING 2022 (2022). https:\/\/doi.org\/10.1162\/coli_a_00426","DOI":"10.1162\/coli_a_00426"},{"key":"18_CR17","unstructured":"Knight, K., Marcu, D.: Statistics-based summarization - step one: sentence compression. In: Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on on Innovative Applications of Artificial Intelligence, 2000. AAAI Press\/The MIT Press (2000)"},{"key":"18_CR18","doi-asserted-by":"publisher","unstructured":"Kumar, D., Mou, L., Golab, L., Vechtomova, O.: Iterative edit-based unsupervised sentence simplification. In: ACL 2020. ACL (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.707","DOI":"10.18653\/v1\/2020.acl-main.707"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL 2020. ACL (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Liu, X., Mou, L., Meng, F., Zhou, H., Zhou, J., Song, S.: Unsupervised paraphrasing by simulated annealing. In: ACL 2020. ACL (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.28","DOI":"10.18653\/v1\/2020.acl-main.28"},{"key":"18_CR21","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR (2019)"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Luoma, J., Pyysalo, S.: Exploring cross-sentence contexts for named entity recognition with BERT. In: Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), 8\u201313 December 2020. International Committee on Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.78","DOI":"10.18653\/v1\/2020.coling-main.78"},{"key":"18_CR23","unstructured":"McKeown, K.R.: Paraphrasing questions using given and new information. Am. J. Comput. Linguist. 9(1), 1\u201310 (1983)"},{"key":"18_CR24","doi-asserted-by":"publisher","unstructured":"Motrichenko, D., Nedumov, Y., Skorniakov, K.: Bag of tricks for citation intent classification via SciBERT. In: 2021 Ivannikov Ispras Open Conference (ISPRAS) (2021). https:\/\/doi.org\/10.1109\/ISPRAS53967.2021.00022","DOI":"10.1109\/ISPRAS53967.2021.00022"},{"key":"18_CR25","doi-asserted-by":"publisher","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. CoRR (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.02155","DOI":"10.48550\/arXiv.2203.02155"},{"key":"18_CR26","unstructured":"Prakash, A., et al.: Neural paraphrase generation with stacked residual LSTM networks. In: COLING 2016. ACL (2016)"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Preda, G.: COVID19 Tweets (2020). https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/1451513","DOI":"10.34740\/KAGGLE\/DSV\/1451513"},{"key":"18_CR28","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"18_CR29","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020). Article No. 140"},{"key":"18_CR30","unstructured":"Rajauria, A.: Pegasus paraphraser. https:\/\/huggingface.co\/tuner007\/pegasus_paraphrase. Accessed November 2022"},{"key":"18_CR31","doi-asserted-by":"publisher","unstructured":"Rao, S., Tetreault, J.R.: Dear sir or madam, may i introduce the GYAFC dataset: corpus, benchmarks and metrics for formality style transfer. In: NAACL-HLT 2018. ACL (2018). https:\/\/doi.org\/10.18653\/v1\/n18-1012","DOI":"10.18653\/v1\/n18-1012"},{"key":"18_CR32","unstructured":"Rudnichenko, N., Vychuzhanin, V., Shibaeva, N., Antoshchuk, S., Petrov, I.: Intellectual information system for supporting text data rephrasing processes based on deep learning. In: Proceedings of the 2nd International Workshop on Intelligent Information Technologies & Systems of Information Security with CEUR-WS. CEUR-WS.org (2021)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Rudnicka, K.: Variation of sentence length across time and genre. Diachronic corpora, genre, and language change (2018)","DOI":"10.1075\/scl.85.10rud"},{"issue":"3","key":"18_CR34","doi-asserted-by":"publisher","first-page":"3085","DOI":"10.1007\/s11192-020-03382-z","volume":"125","author":"T Saier","year":"2020","unstructured":"Saier, T., F\u00e4rber, M.: unarXive: a large scholarly data set with publications\u2019 full-text, annotated in-text citations, and links to metadata. Scientometrics 125(3), 3085\u20133108 (2020)","journal-title":"Scientometrics"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Saier, T., Krause, J., F\u00e4rber, M.: unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network. CoRR abs\/2303.14957 (2023)","DOI":"10.1109\/JCDL57899.2023.00020"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Schultz, D.M.: The structure of a scientific paper. Am. Meteorol. Soc. (2009). https:\/\/doi.org\/10.1007\/978-1-935704-03-4_4","DOI":"10.1007\/978-1-935704-03-4_4"},{"key":"18_CR37","unstructured":"Shah, P., et al.: Building a conversational agent overnight with dialogue self-play. CoRR (2018)"},{"key":"18_CR38","doi-asserted-by":"publisher","unstructured":"Wando, B.: Ukraine Conflict Twitter Dataset (2022). https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/4787803","DOI":"10.34740\/KAGGLE\/DSV\/4787803"},{"key":"18_CR39","doi-asserted-by":"publisher","unstructured":"Wang, S., Gupta, R., Chang, N., Baldridge, J.: A task in a suit and a tie: paraphrase generation with semantic augmentation. In: AAAI, IAAI, EAAI 2019, AAAI Press (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33017176","DOI":"10.1609\/aaai.v33i01.33017176"},{"key":"18_CR40","unstructured":"Woodard, J., Nelson, J.: An information theoretic measure of speech recognition performance (1982)"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Wymann, C.: Checkliste Schreibprozess : Ihr Weg zum guten Text: Punkt f\u00fcr Punkt. Verlag Barbara Budrich (2018)","DOI":"10.36198\/9783838549606"},{"key":"18_CR42","unstructured":"Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: PEGASUS: pre-training with extracted gap-sentences forabstractive summarization. In: ICML 2020. PMLR (2020)"},{"key":"18_CR43","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with BERT. In: ICLR 2020. OpenReview.net (2020)"},{"key":"18_CR44","unstructured":"Zhou, J., M\u00fcller, H., Holzinger, A., Chen, F.: Ethical ChatGPT: Concerns, Challenges, and Commandments. CoRR abs\/2305.10646 (2023)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40837-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:32:29Z","timestamp":1710329549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40837-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408366","9783031408373"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40837-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CD-MAKE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Cross-Domain Conference for Machine Learning and Knowledge Extraction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benevento","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cd-make2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cd-make.net\/","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":"30","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":"18","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":"60% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}