{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:19:20Z","timestamp":1776446360574,"version":"3.51.2"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031301100","type":"print"},{"value":"9783031301117","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\/978-3-031-30111-7_27","type":"book-chapter","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T01:02:51Z","timestamp":1681261371000},"page":"311-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SCIEnt: A Semantic-Feature-Based Framework for\u00a0Core Information Extraction from\u00a0Web Pages"],"prefix":"10.1007","author":[{"given":"Zhiwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyuanxiang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanhai","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huawei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Yu, X., Jin, Z.: Web content information extraction based on DOM tree and statistical information. In: 2017 IEEE 17th International Conference on Communication Technology (ICCT), pp. 1308\u20131311. IEEE (2017)","DOI":"10.1109\/ICCT.2017.8359846"},{"issue":"11","key":"27_CR2","doi-asserted-by":"publisher","first-page":"4355","DOI":"10.1007\/s10489-018-1208-0","volume":"48","author":"OY Yuliana","year":"2018","unstructured":"Yuliana, O.Y., Chang, C.H.: A novel alignment algorithm for effective web data extraction from singleton-item pages. Appl. Intell. 48(11), 4355\u20134370 (2018). https:\/\/doi.org\/10.1007\/s10489-018-1208-0","journal-title":"Appl. Intell."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Sun, F., Song, D., Liao, L.: DOM based content extraction via text density. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 245\u2013254 (2011)","DOI":"10.1145\/2009916.2009952"},{"key":"27_CR4","doi-asserted-by":"publisher","first-page":"64085","DOI":"10.1109\/ACCESS.2018.2877592","volume":"6","author":"Z Tan","year":"2018","unstructured":"Tan, Z., He, C., Fang, Y., et al.: Title-based extraction of news contents for text mining. IEEE Access 6, 64085\u201364095 (2018)","journal-title":"IEEE Access"},{"key":"27_CR5","unstructured":"Yao, J., Zuo, X.: A machine learning approach to webpage content exraction (2013)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Utiu, N., Ionescu, V.S.: Learning web content extraction with DOM features. In: 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP), pp. 5\u201311. IEEE (2018)","DOI":"10.1109\/ICCP.2018.8516632"},{"key":"27_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/978-3-030-24268-8_26","volume-title":"Artificial Intelligence and Security","author":"H Yang","year":"2019","unstructured":"Yang, H., Lu, H., Li, S., Li, M., Sun, Y.: Research on content extraction of rich text web pages. In: Sun, X., Pan, Z., Bertino, E. (eds.) ICAIS 2019. LNCS, vol. 11635, pp. 279\u2013287. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-24268-8_26"},{"key":"27_CR8","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"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Leonhardt, J., Anand, A., Khosla, M.: Boilerplate removal using a neural sequence labeling model. In: Companion Proceedings of the Web Conference, pp. 226\u2013229 (2020)","DOI":"10.1145\/3366424.3383547"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Wang, Q., Fang, Y., Ravula, A., et al.: WebFormer: the web-page transformer for structure information extraction. In: Proceedings of the ACM Web Conference, pp. 3124\u20133133 (2022)","DOI":"10.1145\/3485447.3512032"},{"key":"27_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/3-540-36901-5_42","volume-title":"Web Technologies and Applications","author":"D Cai","year":"2003","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: Extracting content structure for web pages based on visual representation. In: Zhou, X., Orlowska, M.E., Zhang, Y. (eds.) APWeb 2003. LNCS, vol. 2642, pp. 406\u2013417. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-36901-5_42"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Zhao, H., Meng, W., Wu, Z., et al.: Fully automatic wrapper generation for search engines. In: Proceedings of the 14th International Conference on World Wide Web, pp. 66\u201375 (2005)","DOI":"10.1145\/1060745.1060760"},{"issue":"3","key":"27_CR13","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1109\/TKDE.2011.175","volume":"25","author":"Y Lu","year":"2011","unstructured":"Lu, Y., He, H., Zhao, H., et al.: Annotating search results from web databases. IEEE Trans. Knowl. Data Eng. 25(3), 514\u2013527 (2011)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Anderson, N., Hong, J.: Visually extracting data records from the deep web. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 1233\u20131238 (2013)","DOI":"10.1145\/2487788.2488156"},{"key":"27_CR15","doi-asserted-by":"publisher","unstructured":"Liu, J., Lin, L., Cai, Z., et al.: Deep web data extraction based on visual information processing. J. Ambient Intell. Human. Comput. 1\u201311 (2017). https:\/\/doi.org\/10.1007\/s12652-017-0587-0","DOI":"10.1007\/s12652-017-0587-0"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Kumar, A., Morabia, K., Wang, J., et al.: CoVA: context-aware visual attention for webpage information extraction. arXiv preprint arXiv:2110.12320, 2021","DOI":"10.18653\/v1\/2022.ecnlp-1.11"},{"key":"27_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR18","unstructured":"Baroni, M., Chantree, F., Kilgarriff, A., et al.: Cleaneval: a competition for cleaning web pages. In: Lrec (2008)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30111-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:26:05Z","timestamp":1776443165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30111-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031301100","9783031301117"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30111-7_27","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":"13 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}