{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T20:58:19Z","timestamp":1765486699816,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030916688"},{"type":"electronic","value":"9783030916695"}],"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-91669-5_4","type":"book-chapter","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T00:03:08Z","timestamp":1638230588000},"page":"43-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DataQuest: An\u00a0Approach to\u00a0Automatically Extract Dataset Mentions from\u00a0Scientific Papers"],"prefix":"10.1007","author":[{"given":"Sandeep","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tirthankar","family":"Ghosal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asif","family":"Ekbal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,30]]},"reference":[{"unstructured":"The coleridge initiative announces rich context competition\u2014NYU cusp. https:\/\/cusp.nyu.edu\/blog\/the-coleridge-initiative-announces-rich-context-competition\/. Accessed 14 July 2021","key":"4_CR1"},{"unstructured":"Github - rich-context-competition\/rich-context-book-2019. https:\/\/github.com\/rich-context-competition\/rich-context-book-2019. Accessed 14 July 2021","key":"4_CR2"},{"unstructured":"Rich context project - coleridge initiative. https:\/\/coleridgeinitiative.org\/rich-context-project\/. Accessed 14 July 2021","key":"4_CR3"},{"unstructured":"Richcontextcompetition - coleridge initiative. https:\/\/coleridgeinitiative.org\/richcontext\/richcontextcompetition\/. Accessed 14 July 2021","key":"4_CR4"},{"unstructured":"Spacy industrial-strength natural language processing in python. https:\/\/spacy.io\/. Accessed 15 July 2021","key":"4_CR5"},{"doi-asserted-by":"crossref","unstructured":"Cohan, A., Beltagy, I., King, D., Dalvi, B., Weld, D.S.: Pretrained language models for sequential sentence classification. In: EMNLP (2019)","key":"4_CR6","DOI":"10.18653\/v1\/D19-1383"},{"doi-asserted-by":"publisher","unstructured":"Beltagy, I., Lo, K., Cohan, A.: SciBERT: a pretrained language model for scientific text. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) 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, Hong Kong, China, 3\u20137 November 2019, pp. 3613\u20133618. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1371","key":"4_CR7","DOI":"10.18653\/v1\/D19-1371"},{"key":"4_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/978-3-642-33290-6_17","volume-title":"Theory and Practice of Digital Libraries","author":"K Boland","year":"2012","unstructured":"Boland, K., Ritze, D., Eckert, K., Mathiak, B.: Identifying references to datasets in publications. In: Zaphiris, P., Buchanan, G., Rasmussen, E., Loizides, F. (eds.) TPDL 2012. LNCS, vol. 7489, pp. 150\u2013161. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33290-6_17"},{"issue":"3","key":"4_CR9","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1093\/jamia\/ocx121","volume":"25","author":"X Chen","year":"2018","unstructured":"Chen, X., et al.: DataMed - an open source discovery index for finding biomedical datasets. J. Am. Medical Informatics Assoc. 25(3), 300\u2013308 (2018)","journal-title":"J. Am. Medical Informatics Assoc."},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2019)","key":"4_CR10"},{"doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019 (Long and Short Papers), vol. 1, pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","key":"4_CR11","DOI":"10.18653\/v1\/n19-1423"},{"unstructured":"Feger, S.S.: Interactive tools for reproducible science - understanding, supporting, and motivating reproducible science practices. CoRR abs\/2012.02570 (2020). https:\/\/arxiv.org\/abs\/2012.02570","key":"4_CR12"},{"doi-asserted-by":"crossref","unstructured":"Gardner, M., et al.: AllenNLP: a deep semantic natural language processing platform (2018). http:\/\/arxiv.org\/abs\/1803.07640","key":"4_CR13","DOI":"10.18653\/v1\/W18-2501"},{"issue":"3\u20134","key":"4_CR14","first-page":"171","volume":"36","author":"B Ghavimi","year":"2016","unstructured":"Ghavimi, B., Mayr, P., Lange, C., Vahdati, S., Auer, S.: A semi-automatic approach for detecting dataset references in social science texts. Inf. Serv. Use 36(3\u20134), 171\u2013187 (2016)","journal-title":"Inf. Serv. Use"},{"doi-asserted-by":"publisher","unstructured":"Ghavimi, B., Mayr, P., Vahdati, S., Lange, C.: Identifying and improving dataset references in social sciences full texts. In: Loizides, F., Schmidt, B. (eds.) Positioning and Power in Academic Publishing: Players, Agents and Agendas, 20th International Conference on Electronic Publishing, G\u00f6ttingen, Germany, 7\u20139 June 2016, pp. 105\u2013114. IOS Press (2016). https:\/\/doi.org\/10.3233\/978-1-61499-649-1-105","key":"4_CR15","DOI":"10.3233\/978-1-61499-649-1-105"},{"unstructured":"Grover, M.: Amundsen - Lyft\u2019s data discovery & metadata engine\u2014by mark grover\u2014Lyft engineering, April 2019. https:\/\/eng.lyft.com\/amundsen-lyfts-data-discovery-metadata-engine-62d27254fbb9. Accessed 31 Oct 2020","key":"4_CR16"},{"unstructured":"Hong, G., Cao, M.S., Puerto-San-Roman, H.: Rich text competition. In: Rich Search and Discovery for Research Datasets: Building the Next Generation of Scholarly Infrastructure. Sage, London (2020)","key":"4_CR17"},{"unstructured":"King, D., Ammar, W., Beltagy, I., Betts, C., Gururangan, S., van Zuylen, M.: The AI2 submission at the rich context competition. In: Rich Search and Discovery for Research Datasets: Building the Next Generation of Scholarly Infrastructure. Sage, London (2020)","key":"4_CR18"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2015). http:\/\/arxiv.org\/abs\/1412.6980","key":"4_CR19"},{"doi-asserted-by":"crossref","unstructured":"Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. CoRR abs\/1603.01360 (2016). http:\/\/arxiv.org\/abs\/1603.01360","key":"4_CR20","DOI":"10.18653\/v1\/N16-1030"},{"doi-asserted-by":"crossref","unstructured":"Lu, M., Bangalore, S., Cormode, G., Hadjieleftheriou, M., Srivastava, D.: A dataset search engine for the research document corpus. In: 2012 IEEE 28th International Conference on Data Engineering, pp. 1237\u20131240. IEEE (2012)","key":"4_CR21","DOI":"10.1109\/ICDE.2012.80"},{"doi-asserted-by":"publisher","unstructured":"Munaf\u00f2, M., et al.: A manifesto for reproducible science. Nat. Hum. Behav. 1, 0021 (2017). https:\/\/doi.org\/10.1038\/s41562-016-0021","key":"4_CR22","DOI":"10.1038\/s41562-016-0021"},{"issue":"3","key":"4_CR23","doi-asserted-by":"publisher","first-page":"1931","DOI":"10.1007\/s11192-018-2921-5","volume":"117","author":"Z Nasar","year":"2018","unstructured":"Nasar, Z., Jaffry, S.W., Malik, M.K.: Information extraction from scientific articles: a survey. Scientometrics 117(3), 1931\u20131990 (2018)","journal-title":"Scientometrics"},{"unstructured":"Ngonga, P.D.A., Srivastava, N., Jalota, R.: Dice @ rich context competition. In: Rich Search and Discovery for Research Datasets: Building the Next Generation of Scholarly Infrastructure. Sage, London (2020)","key":"4_CR24"},{"key":"4_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/978-3-540-77094-7_41","volume-title":"Asian Digital Libraries. Looking Back 10 Years and Forging New Frontiers","author":"TD Nguyen","year":"2007","unstructured":"Nguyen, T.D., Kan, M.-Y.: Keyphrase extraction in scientific publications. In: Goh, D.H.-L., Cao, T.H., S\u00f8lvberg, I.T., Rasmussen, E. (eds.) ICADL 2007. LNCS, vol. 4822, pp. 317\u2013326. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-77094-7_41"},{"unstructured":"Noy, N., Burgess, M., Brickley, D.: Google dataset search: building a search engine for datasets in an open web ecosystem. In: 28th Web Conference (WebConf 2019) (2019)","key":"4_CR26"},{"unstructured":"Otto, W., Zielinski, A., Ghavimi, B., Dimitrov, D., Tavakolpoursaleh, N.: Rich context competition phase 2. In: Rich Search and Discovery for Research Datasets: Building the Next Generation of Scholarly Infrastructure. Sage, London (2020)","key":"4_CR27"},{"issue":"4","key":"4_CR28","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1016\/j.ipm.2005.09.002","volume":"42","author":"F Peng","year":"2006","unstructured":"Peng, F., McCallum, A.: Information extraction from research papers using conditional random fields. Inf. Process. Manag. 42(4), 963\u2013979 (2006)","journal-title":"Inf. Process. Manag."},{"doi-asserted-by":"publisher","unstructured":"Prasad, A., Si, C., Kan, M.Y.: Dataset mention extraction and classification. In: Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications, Minneapolis, Minnesota, pp. 31\u201336. Association for Computational Linguistics, June 2019. https:\/\/doi.org\/10.18653\/v1\/W19-2604. https:\/\/www.aclweb.org\/anthology\/W19-2604","key":"4_CR29","DOI":"10.18653\/v1\/W19-2604"},{"unstructured":"Prasetyo, P.K., Silva, A., Lim, E.P., Achananuparp, P.: Simple extraction for social science publications. In: Rich Search and Discovery for Research Datasets: Building the Next Generation of Scholarly Infrastructure. Sage, London (2020)","key":"4_CR30"},{"unstructured":"Shamsfard, M., Jafari, H.S., Ilbeygi, M.: Step-1: a set of fundamental tools for Persian text processing. In: Calzolari, N., et al. (eds.) Proceedings of the International Conference on Language Resources and Evaluation, LREC 2010, Valletta, Malta, 17\u201323 May 2010. European Language Resources Association (2010). http:\/\/www.lrec-conf.org\/proceedings\/lrec2010\/summaries\/809.html","key":"4_CR31"},{"doi-asserted-by":"crossref","unstructured":"Singhal, A., Srivastava, J.: Research dataset discovery from research publications using web context. In: Web Intelligence, vol. 15, pp. 81\u201399. IOS Press (2017)","key":"4_CR32","DOI":"10.3233\/WEB-170354"},{"unstructured":"Zeng, T., Acuna, D.: Dataset mention extraction in scientific articles using a BiLSTM-CRF model. In: Rich Search and Discovery for Research Datasets: Building the Next Generation of Scholarly Infrastructure. Sage, London (2020)","key":"4_CR33"}],"container-title":["Lecture Notes in Computer Science","Towards Open and Trustworthy Digital Societies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-91669-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:55:00Z","timestamp":1709826900000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-91669-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030916688","9783030916695"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-91669-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICADL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Asian Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icadl2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icadl.net\/icadl2021\/","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":"87","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":"17","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":"14","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":"20% - 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":"3.01","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":"4.61","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)"}}]}}