{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:06:34Z","timestamp":1743059194756,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030821463"},{"type":"electronic","value":"9783030821470"}],"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\/978-3-030-82147-0_14","type":"book-chapter","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T23:26:36Z","timestamp":1628292396000},"page":"163-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Dataset Creation Heuristics for Concept Detection in Web Pages Using BERT"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2077-6984","authenticated-orcid":false,"given":"Michael","family":"Paris","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3271-9653","authenticated-orcid":false,"given":"Robert","family":"J\u00e4schke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,7]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Al-Smadi, M., Qawasmeh, O., Talafha, B., Quwaider, M.: Human annotated Arabic dataset of book reviews for aspect based sentiment analysis. In: 3rd International Conference on Future Internet of Things and Cloud, pp. 726\u2013730. IEEE (2015)","DOI":"10.1109\/FiCloud.2015.62"},{"key":"14_CR2","unstructured":"Baroni, M., Chantree, F., Kilgarriff, A., Sharoff, S.: Cleaneval: a competition for cleaning web pages. In: Proc. of the International Conference on Language Resources and Evaluation. LREC, European Language Resources Association (2008)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Ben-David, A., Amram, A.: Computational methods for web history. The SAGE handbook of web history, pp. 153\u2013167 (2019)","DOI":"10.4135\/9781526470546.n12"},{"issue":"6","key":"14_CR4","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1177\/0894439316671698","volume":"35","author":"G Blank","year":"2017","unstructured":"Blank, G.: The digital divide among Twitter users and its implications for social research. Soc. Sci. Comput. Rev. 35(6), 679\u2013697 (2017)","journal-title":"Soc. Sci. Comput. Rev."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Bommasani, R., Cardie, C.: Intrinsic evaluation of summarization datasets. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 8075\u20138096. EMNLP, Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.649"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Brill, E., Wu, J.: Classifier combination for improved lexical disambiguation. In: Annual Meeting of the Association for Computational Linguistics, pp. 191\u2013195. Association for Computational Linguistics (1998)","DOI":"10.3115\/980845.980876"},{"key":"14_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-45439-5_40","volume-title":"Advances in Information Retrieval","author":"A C\u00e2mara","year":"2020","unstructured":"C\u00e2mara, A., Hauff, C.: Diagnosing BERT with retrieval heuristics. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12035, pp. 605\u2013618. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45439-5_40"},{"key":"14_CR8","unstructured":"Derczynski, L.: Complementarity, F-score, and NLP evaluation. In: Proc. of the International Conference on Language Resources and Evaluation, pp. 261\u2013266. LREC, European Language Resources Association (2016)"},{"key":"14_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 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. NAACL, Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Ein-Dor, L., et al.: Financial event extraction using wikipedia-based weak supervision. In: Proceedings of the Second Workshop on Economics and Natural Language Processing (2019)","DOI":"10.18653\/v1\/D19-5102"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Ferrari, A., Spagnolo, G.O., Gnesi, S.: Pure: a dataset of public requirements documents. In: International Requirements Engineering Conference (2017)","DOI":"10.1109\/RE.2017.29"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Gardner, M., et al.: Evaluating models\u2019 local decision boundaries via contrast sets (2020), arxiv:2004.02709","DOI":"10.18653\/v1\/2020.findings-emnlp.117"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Geva, M., Goldberg, Y., Berant, J.: Are we modeling the task or the annotator? an investigation of annotator bias in natural language understanding datasets (2019), arXiv:1908.07898","DOI":"10.18653\/v1\/D19-1107"},{"key":"14_CR14","unstructured":"International Internet Preservation Consortium (IIPC): The WARC Format 1.1. https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/#warc-file-name-size-and-compression, [Online; Last accessed 11 Mar 2021]"},{"issue":"4","key":"14_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3239574","volume":"10","author":"J Kiesel","year":"2018","unstructured":"Kiesel, J., Kneist, F., Alshomary, M., Stein, B., Hagen, M., Potthast, M.: Reproducible web corpora: interactive archiving with automatic quality assessment. J. Data ad Inf. Quality 10(4), 1\u201325 (2018)","journal-title":"J. Data ad Inf. Quality"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Lehmann, J., et\u00a0al.: DBpedia \u2013 a large-scale, multilingual knowledge base extracted from Wikipedia. Semantic Web 6(2) (2015)","DOI":"10.3233\/SW-140134"},{"issue":"2","key":"14_CR17","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.14778\/1687553.1687577","volume":"2","author":"M Ley","year":"2009","unstructured":"Ley, M.: DBLP: some lessons learned. Proc. VLDB Endowment 2(2), 1493\u20131500 (2009)","journal-title":"Proc. VLDB Endowment"},{"issue":"4","key":"14_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3097570","volume":"10","author":"J Lin","year":"2017","unstructured":"Lin, J., Milligan, I., Wiebe, J., Zhou, A.: Warcbase: scalable analytics infrastructure for exploring web archives. J. Comput. Cultural Heritage 10(4), 1\u201330 (2017)","journal-title":"J. Comput. Cultural Heritage"},{"key":"14_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"14_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-030-62077-6_14","volume-title":"Logic, Language, and Security","author":"K Lu","year":"2020","unstructured":"Lu, K., Mardziel, P., Wu, F., Amancharla, P., Datta, A.: Gender bias in neural natural language processing. In: Nigam, V., et al. (eds.) Logic, Language, and Security. LNCS, vol. 12300, pp. 189\u2013202. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-62077-6_14"},{"key":"14_CR21","unstructured":"Mohammad, S.M.: NLP scholar: a dataset for examining the state of NLP research. In: Proceedings of the Language Resources and Evaluation Conference. ELRA (2020)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Paris, M., J\u00e4schke, R.: How to assess the exhaustiveness of longitudinal web archives. In: Proceedings of the Conference on Hypertext and Social Media. ACM (2020)","DOI":"10.1145\/3372923.3404836"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Peng, Y., Yan, S., Lu, Z.: Transfer learning in biomedical natural language processing: an evaluation of bert and elmo on ten benchmarking datasets. arXiv preprint arXiv:1906.05474 (2019)","DOI":"10.18653\/v1\/W19-5006"},{"issue":"5","key":"14_CR24","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s10791-015-9261-3","volume":"18","author":"Y Qian","year":"2015","unstructured":"Qian, Y., Zheng, Q., Sakai, T., Ye, J., Liu, J.: Dynamic author name disambiguation for growing digital libraries. Inf. Retrieval J. 18(5), 379\u2013412 (2015). https:\/\/doi.org\/10.1007\/s10791-015-9261-3","journal-title":"Inf. Retrieval J."},{"key":"14_CR25","first-page":"1419","volume":"6","author":"M Strube","year":"2006","unstructured":"Strube, M., Ponzetto, S.P.: Wikirelate! computing semantic relatedness using wikipedia. AAAI 6, 1419\u20131424 (2006)","journal-title":"AAAI"},{"issue":"1","key":"14_CR26","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s42803-019-00007-7","volume":"1","author":"E Vlassenroot","year":"2019","unstructured":"Vlassenroot, E., et al.: Web archives as a data resource for digital scholars. Int. J. Digital Humanities 1(1), 85\u2013111 (2019). https:\/\/doi.org\/10.1007\/s42803-019-00007-7","journal-title":"Int. J. Digital Humanities"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/978-3-319-76941-7_13","volume-title":"Advances in Information Retrieval","author":"T Vogels","year":"2018","unstructured":"Vogels, T., Ganea, O.-E., Eickhoff, C.: Web2Text: deep structured boilerplate removal. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds.) ECIR 2018. LNCS, vol. 10772, pp. 167\u2013179. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-76941-7_13"},{"issue":"10","key":"14_CR28","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014)","journal-title":"Commun. ACM"},{"key":"14_CR29","unstructured":"Wolf, T., et al.: Transformers: State-of-the-art natural language processing. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 38\u201345. EMNLP, Association for Computational Linguistics (2020)"},{"key":"14_CR30","first-page":"1646","volume":"8","author":"T Zesch","year":"2008","unstructured":"Zesch, T., M\u00fcller, C., Gurevych, I.: Extracting lexical semantic knowledge from Wikipedia and Wiktionary. LREC 8, 1646\u20131652 (2008)","journal-title":"LREC"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82147-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T23:57:54Z","timestamp":1628294274000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82147-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030821463","9783030821470"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82147-0_14","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":"7 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"14 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cloud-conf.net\/ksem21\/index.html","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":"492","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":"164","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":"33% - 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":"10","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)"}}]}}